Audio Action Set: Syntax

Provides actions for processing audio data

computeFeatures Action

Compute various features for audio files loaded into a Cloud Analytic Services table.

CASL Syntax

audio.computeFeatures <result=results> <status=rc> /

audioColumn="string"

casOut={

caslib="string",

compress=TRUE | FALSE,

indexVars={"variable-name-1" <, "variable-name-2", ...>},

label="string",

maxMemSize=64-bit-integer,

name="table-name",

onDemand=TRUE | FALSE,

promote=TRUE | FALSE,

replace=TRUE | FALSE,

replication=integer,

timeStamp="string",

where={"string-1" <, "string-2", ...>}

}

copyVars={"variable-name-1" <, "variable-name-2", ...>}

fbankOptions={

energyFloor=double,

rawEnergy=TRUE | FALSE,

useEnergy=TRUE | FALSE,

useLogFbank=TRUE | FALSE,

usePower=TRUE | FALSE

}

featureScalingMethod="NONE" | "STANDARDIZATION"

frameExtractionOptions={

blackmanCoeff=double,

dither=double,

frameLength=double,

frameShift=double,

preemphCoeff=double,

removeDcOffset=TRUE | FALSE,

roundToPowerOfTwo=TRUE | FALSE,

snipEdges=TRUE | FALSE,

windowType="BLACKMAN" | "HAMMING" | "HANNING" | "RECTANGULAR"

}

melBanksOptions={

highFreq=double,

lowFreq=double,

nBins=integer

}

mfccOptions={

cepstralLifter=double,

energyFloor=double,

nCeps=integer,

rawEnergy=TRUE | FALSE,

useEnergy=TRUE | FALSE

}

nContextFrames=integer

nOutputFrames=integer

plpOptions={

cepstralLifter=integer,

cepstralScale=double,

compressFactor=double,

energyFloor=double,

lpcOrder=integer,

nCeps=integer,

rawEnergy=TRUE | FALSE,

useEnergy=TRUE | FALSE

}

table={

caslib="string",

computedOnDemand=TRUE | FALSE,

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

computedVarsProgram="string",

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>},

importOptions={fileType="AUTO" | "BASESAS" | "CSV" | "DOCUMENT" | "DTA" | "ESP" | "EXCEL" | "FMT" | "HDAT" | "JMP" | "LASR" | "SPSS" | "XLS", fileType-specific-parameters},

name="table-name",

onDemand=TRUE | FALSE,

singlePass=TRUE | FALSE,

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

where="where-expression"

}

;

Parameter Descriptions

audioColumn="string"

specifies the name of the column in the input table containing the audio data

* casOut={casouttable}

specifies the settings for an output table.

For more information about specifying the casOut parameter, see the common casouttable parameter (Appendix A: Common Parameters).

copyVars={"variable-name-1" <, "variable-name-2", ...>}

specifies the list of variables to transfer from the input table to the output table

Requirement

The specified values must be unique.

fbankOptions={fbankOptions}

specifies the settings used to determine how to perform the FBank feature computations

energyFloor=double

specifies the linear floor on energy (absolute, not relative) for the FBank feature computations

Default	0
Minimum value	0

rawEnergy=TRUE | FALSE

specifies that energy should be computed before preemphasis and windowing

Default

TRUE

useEnergy=TRUE | FALSE

specifies that an extra dimension containing the computed energy should be appended to each FBank feature frame

Default

FALSE

useLogFbank=TRUE | FALSE

specifies that the output should contain log-filterbank values (otherwise, the output values are linear)

Default

TRUE

usePower=TRUE | FALSE

specifies that power should be used in the FBank feature computations (otherwise, the magnitude is used)

Default

TRUE

featureScalingMethod="NONE" | "STANDARDIZATION"

specifies the feature scaling method to apply to the computed feature vectors

Default

NONE

specifies that no feature scaling method should be applied to the computed feature vectors

STANDARDIZATION

specifies that the set containing the same coefficient across all frames in an audio file should be scaled so that the resulting set has a mean of zero and unit variance

frameExtractionOptions={frameExtractionOptions}

specifies the settings used to determine how to break the audio file into frames

blackmanCoeff=double

specifies the constant coefficient used for the generalized Blackman window (this value is ignored for other window types)

Default

0.42

dither=double

specifies the dithering constant (0.0 means no dithering)

Default

frameLength=double

specifies the length of a frame (in milliseconds)

Default	25
Minimum value (exclusive)	0

frameShift=double

specifies the time difference (in milliseconds) between the beginnings of consecutive frames

Default	10
Minimum value (exclusive)	0

preemphCoeff=double

specifies the coefficient used in performing signal preemphasis

Default

0.97

removeDcOffset=TRUE | FALSE

specifies that the mean of the values in each frame should be subtracted from all values in that frame

Default

TRUE

roundToPowerOfTwo=TRUE | FALSE

specifies that the window size should be rounded to the next power of two

Default

TRUE

snipEdges=TRUE | FALSE

specifies that end effects should be handled by outputting only frames that completely fit the data

Default

TRUE

windowType="BLACKMAN" | "HAMMING" | "HANNING" | "RECTANGULAR"

specifies the type of window to apply to each frame upon extraction

Default

RECTANGULAR

BLACKMAN

specifies that a Blackman window should be applied when extracting frames

HAMMING

specifies that a Hamming window should be applied when extracting frames

HANNING

specifies that a Hanning window should be applied when extracting frames

RECTANGULAR

specifies that a rectangular window should be applied when extracting frames

melBanksOptions={melBanksOptions}

specifies the settings used to determine the mel-frequency banks

highFreq=double

specifies the high cutoff frequency for the mel-frequency bins (if negative, the value is added to the Nyquist frequency, which is determined from the sampling rate of the audio)

Default

lowFreq=double

specifies the low cutoff frequency for the mel-frequency bins

Default

nBins=integer

specifies the number of triangular mel-frequency bins

Default	23
Minimum value	1

mfccOptions={mfccOptions}

specifies the settings used to determine how to perform the MFCC feature computations

cepstralLifter=double

specifies the constant which controls the scaling of the MFCC feature values

Default

energyFloor=double

specifies the linear floor on energy (absolute, not relative) for the MFCC feature computations

Default	0
Minimum value	0

nCeps=integer

specifies the number of cepstral coefficients in each MFCC feature frame (including C0)

Default	13
Minimum value	1

rawEnergy=TRUE | FALSE

specifies that energy should be computed before preemphasis and windowing

Default

TRUE

useEnergy=TRUE | FALSE

specifies that energy (not C0) should be used in the MFCC feature computations

Default

TRUE

nContextFrames=integer

specifies the number of context frames to append before and after the current audio frame

Default	0
Minimum value	0

nOutputFrames=integer

specifies the exact number of frames to include in the output table (extra frames are dropped and missing frames are padded with zeros)

Minimum value

plpOptions={plpOptions}

specifies the settings used to determine how to perform the PLP feature computations

cepstralLifter=integer

specifies the constant which controls the scaling of the PLP feature values

Default

cepstralScale=double

specifies the cepstral scaling constant used in the PLP computation

Default	1
Minimum value (exclusive)	0

compressFactor=double

specifies the compression factor used in the PLP feature computations

Default	0.33333
Minimum value (exclusive)	0

energyFloor=double

specifies the linear floor on energy (absolute, not relative) for the PLP feature computations

Default	0
Minimum value	0

lpcOrder=integer

specifies the order of the linear predictive coding (LPC) analysis used in the PLP feature computations

Default	12
Minimum value	1

nCeps=integer

specifies the number of cepstral coefficients in each PLP feature frame (including C0)

Default	13
Minimum value	1

rawEnergy=TRUE | FALSE

specifies that energy should be computed before preemphasis and windowing

Default

TRUE

useEnergy=TRUE | FALSE

specifies that energy (not C0) should be used for the zeroth feature value in the PLP feature computations

Default

TRUE

* table={castable}

specifies the settings for an input table.

Long form	table={name="table-name"}
Shortcut form	table="table-name"

The castable value can be one or more of the following:

caslib="string"

specifies the caslib that contains the table that you want to use with the action. By default, the active caslib is used. Specify a value only if you need to access a table from a different caslib.

computedOnDemand=TRUE | FALSE

when set to True, creates the computed variables when the table is loaded instead of when the action begins.

Alias	compOnDemand
Default	FALSE

computedVars={{casinvardesc-1} <, {casinvardesc-2}, ...>}

specifies the names of the computed variables to create. Specify an expression for each variable in the computedVarsProgram parameter.

Alias

compVars

format="string"

specifies the format to apply to the variable.

formattedLength=integer

specifies the length of format field plus the format precision.

label="string"

specifies the descriptive label for the variable.

* name="variable-name"

specifies the name for the variable.

nfd=integer

specifies the length of the format precision.

nfl=integer

specifies the length of the format field.

computedVarsProgram="string"

specifies an expression for each computed variable that you include in the computedVars parameter.

Alias

compPgm

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>}

specifies data source options.

Alias

options, dataSource

importOptions={fileType="AUTO" | "BASESAS" | "CSV" | "DOCUMENT" | "DTA" | "ESP" | "EXCEL" | "FMT" | "HDAT" | "JMP" | "LASR" | "SPSS" | "XLS", fileType-specific-parameters}

specifies the settings for reading a table from a data source.

Alias

import

The value that you specify for fileType determines the other parameters that apply. For more information about this common parameter, see importOptions (Appendix A: Common Parameters).

* name="table-name"

specifies the name of the table to use.

onDemand=TRUE | FALSE

This parameter is deprecated.

Default

TRUE

singlePass=TRUE | FALSE

when set to True, does not create a transient table on the server. Setting this parameter to True can be efficient, but the data might not have stable ordering upon repeated runs.

Default

FALSE

vars={{casinvardesc-1} <, {casinvardesc-2}, ...>}

specifies the variables to use in the action.

format="string"

specifies the format to apply to the variable.

formattedLength=integer

specifies the length of format field plus the format precision.

label="string"

specifies the descriptive label for the variable.

* name="variable-name"

specifies the name for the variable.

nfd=integer

specifies the length of the format precision.

nfl=integer

specifies the length of the format field.

where="where-expression"

specifies an expression for subsetting the input data.

computeFeatures Action

Compute various features for audio files loaded into a Cloud Analytic Services table.

Lua Syntax

results, info = s:audio_computeFeatures{

audioColumn="string",

casOut={

caslib="string",

compress=true | false,

indexVars={"variable-name-1" <, "variable-name-2", ...>},

label="string",

maxMemSize=64-bit-integer,

name="table-name",

onDemand=true | false,

promote=true | false,

replace=true | false,

replication=integer,

timeStamp="string",

where={"string-1" <, "string-2", ...>}

copyVars={"variable-name-1" <, "variable-name-2", ...>},

fbankOptions={

energyFloor=double,

rawEnergy=true | false,

useEnergy=true | false,

useLogFbank=true | false,

usePower=true | false

featureScalingMethod="NONE" | "STANDARDIZATION",

frameExtractionOptions={

blackmanCoeff=double,

dither=double,

frameLength=double,

frameShift=double,

preemphCoeff=double,

removeDcOffset=true | false,

roundToPowerOfTwo=true | false,

snipEdges=true | false,

windowType="BLACKMAN" | "HAMMING" | "HANNING" | "RECTANGULAR"

melBanksOptions={

highFreq=double,

lowFreq=double,

nBins=integer

mfccOptions={

cepstralLifter=double,

energyFloor=double,

nCeps=integer,

rawEnergy=true | false,

useEnergy=true | false

nContextFrames=integer,

nOutputFrames=integer,

plpOptions={

cepstralLifter=integer,

cepstralScale=double,

compressFactor=double,

energyFloor=double,

lpcOrder=integer,

nCeps=integer,

rawEnergy=true | false,

useEnergy=true | false

table={

caslib="string",

computedOnDemand=true | false,

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

computedVarsProgram="string",

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>},

importOptions={fileType="AUTO" | "BASESAS" | "CSV" | "DOCUMENT" | "DTA" | "ESP" | "EXCEL" | "FMT" | "HDAT" | "JMP" | "LASR" | "SPSS" | "XLS", fileType-specific-parameters},

name="table-name",

onDemand=true | false,

singlePass=true | false,

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

where="where-expression"

}

Parameter Descriptions

audioColumn="string"

specifies the name of the column in the input table containing the audio data

* casOut={casouttable}

specifies the settings for an output table.

For more information about specifying the casOut parameter, see the common casouttable parameter (Appendix A: Common Parameters).

copyVars={"variable-name-1" <, "variable-name-2", ...>}

specifies the list of variables to transfer from the input table to the output table

Requirement

The specified values must be unique.

fbankOptions={fbankOptions}

specifies the settings used to determine how to perform the FBank feature computations

energyFloor=double

specifies the linear floor on energy (absolute, not relative) for the FBank feature computations

Default	0
Minimum value	0

rawEnergy=true | false

specifies that energy should be computed before preemphasis and windowing

Default

true

useEnergy=true | false

specifies that an extra dimension containing the computed energy should be appended to each FBank feature frame

Default

false

useLogFbank=true | false

specifies that the output should contain log-filterbank values (otherwise, the output values are linear)

Default

true

usePower=true | false

specifies that power should be used in the FBank feature computations (otherwise, the magnitude is used)

Default

true

featureScalingMethod="NONE" | "STANDARDIZATION"

specifies the feature scaling method to apply to the computed feature vectors

Default

NONE

specifies that no feature scaling method should be applied to the computed feature vectors

STANDARDIZATION

specifies that the set containing the same coefficient across all frames in an audio file should be scaled so that the resulting set has a mean of zero and unit variance

frameExtractionOptions={frameExtractionOptions}

specifies the settings used to determine how to break the audio file into frames

blackmanCoeff=double

specifies the constant coefficient used for the generalized Blackman window (this value is ignored for other window types)

Default

0.42

dither=double

specifies the dithering constant (0.0 means no dithering)

Default

frameLength=double

specifies the length of a frame (in milliseconds)

Default	25
Minimum value (exclusive)	0

frameShift=double

specifies the time difference (in milliseconds) between the beginnings of consecutive frames

Default	10
Minimum value (exclusive)	0

preemphCoeff=double

specifies the coefficient used in performing signal preemphasis

Default

0.97

removeDcOffset=true | false

specifies that the mean of the values in each frame should be subtracted from all values in that frame

Default

true

roundToPowerOfTwo=true | false

specifies that the window size should be rounded to the next power of two

Default

true

snipEdges=true | false

specifies that end effects should be handled by outputting only frames that completely fit the data

Default

true

windowType="BLACKMAN" | "HAMMING" | "HANNING" | "RECTANGULAR"

specifies the type of window to apply to each frame upon extraction

Default

RECTANGULAR

BLACKMAN

specifies that a Blackman window should be applied when extracting frames

HAMMING

specifies that a Hamming window should be applied when extracting frames

HANNING

specifies that a Hanning window should be applied when extracting frames

RECTANGULAR

specifies that a rectangular window should be applied when extracting frames

melBanksOptions={melBanksOptions}

specifies the settings used to determine the mel-frequency banks

highFreq=double

specifies the high cutoff frequency for the mel-frequency bins (if negative, the value is added to the Nyquist frequency, which is determined from the sampling rate of the audio)

Default

lowFreq=double

specifies the low cutoff frequency for the mel-frequency bins

Default

nBins=integer

specifies the number of triangular mel-frequency bins

Default	23
Minimum value	1

mfccOptions={mfccOptions}

specifies the settings used to determine how to perform the MFCC feature computations

cepstralLifter=double

specifies the constant which controls the scaling of the MFCC feature values

Default

energyFloor=double

specifies the linear floor on energy (absolute, not relative) for the MFCC feature computations

Default	0
Minimum value	0

nCeps=integer

specifies the number of cepstral coefficients in each MFCC feature frame (including C0)

Default	13
Minimum value	1

rawEnergy=true | false

specifies that energy should be computed before preemphasis and windowing

Default

true

useEnergy=true | false

specifies that energy (not C0) should be used in the MFCC feature computations

Default

true

nContextFrames=integer

specifies the number of context frames to append before and after the current audio frame

Default	0
Minimum value	0

nOutputFrames=integer

specifies the exact number of frames to include in the output table (extra frames are dropped and missing frames are padded with zeros)

Minimum value

plpOptions={plpOptions}

specifies the settings used to determine how to perform the PLP feature computations

cepstralLifter=integer

specifies the constant which controls the scaling of the PLP feature values

Default

cepstralScale=double

specifies the cepstral scaling constant used in the PLP computation

Default	1
Minimum value (exclusive)	0

compressFactor=double

specifies the compression factor used in the PLP feature computations

Default	0.33333
Minimum value (exclusive)	0

energyFloor=double

specifies the linear floor on energy (absolute, not relative) for the PLP feature computations

Default	0
Minimum value	0

lpcOrder=integer

specifies the order of the linear predictive coding (LPC) analysis used in the PLP feature computations

Default	12
Minimum value	1

nCeps=integer

specifies the number of cepstral coefficients in each PLP feature frame (including C0)

Default	13
Minimum value	1

rawEnergy=true | false

specifies that energy should be computed before preemphasis and windowing

Default

true

useEnergy=true | false

specifies that energy (not C0) should be used for the zeroth feature value in the PLP feature computations

Default

true

* table={castable}

specifies the settings for an input table.

Long form	table={name="table-name"}
Shortcut form	table="table-name"

The castable value can be one or more of the following:

caslib="string"

specifies the caslib that contains the table that you want to use with the action. By default, the active caslib is used. Specify a value only if you need to access a table from a different caslib.

computedOnDemand=true | false

when set to True, creates the computed variables when the table is loaded instead of when the action begins.

Alias	compOnDemand
Default	false

computedVars={{casinvardesc-1} <, {casinvardesc-2}, ...>}

specifies the names of the computed variables to create. Specify an expression for each variable in the computedVarsProgram parameter.

Alias

compVars

format="string"

specifies the format to apply to the variable.

formattedLength=integer

specifies the length of format field plus the format precision.

label="string"

specifies the descriptive label for the variable.

* name="variable-name"

specifies the name for the variable.

nfd=integer

specifies the length of the format precision.

nfl=integer

specifies the length of the format field.

computedVarsProgram="string"

specifies an expression for each computed variable that you include in the computedVars parameter.

Alias

compPgm

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>}

specifies data source options.

Alias

options, dataSource

importOptions={fileType="AUTO" | "BASESAS" | "CSV" | "DOCUMENT" | "DTA" | "ESP" | "EXCEL" | "FMT" | "HDAT" | "JMP" | "LASR" | "SPSS" | "XLS", fileType-specific-parameters}

specifies the settings for reading a table from a data source.

Alias

import

The value that you specify for fileType determines the other parameters that apply. For more information about this common parameter, see importOptions (Appendix A: Common Parameters).

* name="table-name"

specifies the name of the table to use.

onDemand=true | false

This parameter is deprecated.

Default

true

singlePass=true | false

when set to True, does not create a transient table on the server. Setting this parameter to True can be efficient, but the data might not have stable ordering upon repeated runs.

Default

false

vars={{casinvardesc-1} <, {casinvardesc-2}, ...>}

specifies the variables to use in the action.

format="string"

specifies the format to apply to the variable.

formattedLength=integer

specifies the length of format field plus the format precision.

label="string"

specifies the descriptive label for the variable.

* name="variable-name"

specifies the name for the variable.

nfd=integer

specifies the length of the format precision.

nfl=integer

specifies the length of the format field.

where="where-expression"

specifies an expression for subsetting the input data.

computeFeatures Action

Compute various features for audio files loaded into a Cloud Analytic Services table.

Python Syntax

results= s.audio.computeFeatures(

audioColumn="string",

casOut={

"caslib":"string",

"compress":True | False,

"indexVars":["variable-name-1" <, "variable-name-2", ...>],

"label":"string",

"maxMemSize":64-bit-integer,

"name":"table-name",

"onDemand":True | False,

"promote":True | False,

"replace":True | False,

"replication":integer,

"timeStamp":"string",

"where":["string-1" <, "string-2", ...>]

copyVars=["variable-name-1" <, "variable-name-2", ...>],

fbankOptions={

"energyFloor":double,

"rawEnergy":True | False,

"useEnergy":True | False,

"useLogFbank":True | False,

"usePower":True | False

featureScalingMethod="NONE" | "STANDARDIZATION",

frameExtractionOptions={

"blackmanCoeff":double,

"dither":double,

"frameLength":double,

"frameShift":double,

"preemphCoeff":double,

"removeDcOffset":True | False,

"roundToPowerOfTwo":True | False,

"snipEdges":True | False,

"windowType":"BLACKMAN" | "HAMMING" | "HANNING" | "RECTANGULAR"

melBanksOptions={

"highFreq":double,

"lowFreq":double,

"nBins":integer

mfccOptions={

"cepstralLifter":double,

"energyFloor":double,

"nCeps":integer,

"rawEnergy":True | False,

"useEnergy":True | False

nContextFrames=integer,

nOutputFrames=integer,

plpOptions={

"cepstralLifter":integer,

"cepstralScale":double,

"compressFactor":double,

"energyFloor":double,

"lpcOrder":integer,

"nCeps":integer,

"rawEnergy":True | False,

"useEnergy":True | False

table={

"caslib":"string",

"computedOnDemand":True | False,

"computedVars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>],

"computedVarsProgram":"string",

"dataSourceOptions":{"key-1":{any-list-or-data-type-1} <, "key-2":{any-list-or-data-type-2}, ...>},

"importOptions":{"fileType":"AUTO" | "BASESAS" | "CSV" | "DOCUMENT" | "DTA" | "ESP" | "EXCEL" | "FMT" | "HDAT" | "JMP" | "LASR" | "SPSS" | "XLS", fileType-specific-parameters},

"name":"table-name",

"onDemand":True | False,

"singlePass":True | False,

"vars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>],

"where":"where-expression"

}

)

Parameter Descriptions

audioColumn="string"

specifies the name of the column in the input table containing the audio data

* casOut={casouttable}

specifies the settings for an output table.

For more information about specifying the casOut parameter, see the common casouttable parameter (Appendix A: Common Parameters).

copyVars=["variable-name-1" <, "variable-name-2", ...>]

specifies the list of variables to transfer from the input table to the output table

Requirement

The specified values must be unique.

fbankOptions={fbankOptions}

specifies the settings used to determine how to perform the FBank feature computations

"energyFloor":double

specifies the linear floor on energy (absolute, not relative) for the FBank feature computations

Default	0
Minimum value	0

"rawEnergy":True | False

specifies that energy should be computed before preemphasis and windowing

Default

True

"useEnergy":True | False

specifies that an extra dimension containing the computed energy should be appended to each FBank feature frame

Default

False

"useLogFbank":True | False

specifies that the output should contain log-filterbank values (otherwise, the output values are linear)

Default

True

"usePower":True | False

specifies that power should be used in the FBank feature computations (otherwise, the magnitude is used)

Default

True

featureScalingMethod="NONE" | "STANDARDIZATION"

specifies the feature scaling method to apply to the computed feature vectors

Default

NONE

specifies that no feature scaling method should be applied to the computed feature vectors

STANDARDIZATION

specifies that the set containing the same coefficient across all frames in an audio file should be scaled so that the resulting set has a mean of zero and unit variance

frameExtractionOptions={frameExtractionOptions}

specifies the settings used to determine how to break the audio file into frames

"blackmanCoeff":double

specifies the constant coefficient used for the generalized Blackman window (this value is ignored for other window types)

Default

0.42

"dither":double

specifies the dithering constant (0.0 means no dithering)

Default

"frameLength":double

specifies the length of a frame (in milliseconds)

Default	25
Minimum value (exclusive)	0

"frameShift":double

specifies the time difference (in milliseconds) between the beginnings of consecutive frames

Default	10
Minimum value (exclusive)	0

"preemphCoeff":double

specifies the coefficient used in performing signal preemphasis

Default

0.97

"removeDcOffset":True | False

specifies that the mean of the values in each frame should be subtracted from all values in that frame

Default

True

"roundToPowerOfTwo":True | False

specifies that the window size should be rounded to the next power of two

Default

True

"snipEdges":True | False

specifies that end effects should be handled by outputting only frames that completely fit the data

Default

True

"windowType":"BLACKMAN" | "HAMMING" | "HANNING" | "RECTANGULAR"

specifies the type of window to apply to each frame upon extraction

Default

RECTANGULAR

BLACKMAN

specifies that a Blackman window should be applied when extracting frames

HAMMING

specifies that a Hamming window should be applied when extracting frames

HANNING

specifies that a Hanning window should be applied when extracting frames

RECTANGULAR

specifies that a rectangular window should be applied when extracting frames

melBanksOptions={melBanksOptions}

specifies the settings used to determine the mel-frequency banks

"highFreq":double

specifies the high cutoff frequency for the mel-frequency bins (if negative, the value is added to the Nyquist frequency, which is determined from the sampling rate of the audio)

Default

"lowFreq":double

specifies the low cutoff frequency for the mel-frequency bins

Default

"nBins":integer

specifies the number of triangular mel-frequency bins

Default	23
Minimum value	1

mfccOptions={mfccOptions}

specifies the settings used to determine how to perform the MFCC feature computations

"cepstralLifter":double

specifies the constant which controls the scaling of the MFCC feature values

Default

"energyFloor":double

specifies the linear floor on energy (absolute, not relative) for the MFCC feature computations

Default	0
Minimum value	0

"nCeps":integer

specifies the number of cepstral coefficients in each MFCC feature frame (including C0)

Default	13
Minimum value	1

"rawEnergy":True | False

specifies that energy should be computed before preemphasis and windowing

Default

True

"useEnergy":True | False

specifies that energy (not C0) should be used in the MFCC feature computations

Default

True

nContextFrames=integer

specifies the number of context frames to append before and after the current audio frame

Default	0
Minimum value	0

nOutputFrames=integer

specifies the exact number of frames to include in the output table (extra frames are dropped and missing frames are padded with zeros)

Minimum value

plpOptions={plpOptions}

specifies the settings used to determine how to perform the PLP feature computations

"cepstralLifter":integer

specifies the constant which controls the scaling of the PLP feature values

Default

"cepstralScale":double

specifies the cepstral scaling constant used in the PLP computation

Default	1
Minimum value (exclusive)	0

"compressFactor":double

specifies the compression factor used in the PLP feature computations

Default	0.33333
Minimum value (exclusive)	0

"energyFloor":double

specifies the linear floor on energy (absolute, not relative) for the PLP feature computations

Default	0
Minimum value	0

"lpcOrder":integer

specifies the order of the linear predictive coding (LPC) analysis used in the PLP feature computations

Default	12
Minimum value	1

"nCeps":integer

specifies the number of cepstral coefficients in each PLP feature frame (including C0)

Default	13
Minimum value	1

"rawEnergy":True | False

specifies that energy should be computed before preemphasis and windowing

Default

True

"useEnergy":True | False

specifies that energy (not C0) should be used for the zeroth feature value in the PLP feature computations

Default

True

* table={castable}

specifies the settings for an input table.

Long form	table={"name":"table-name"}
Shortcut form	table="table-name"

The castable value can be one or more of the following:

"caslib":"string"

specifies the caslib that contains the table that you want to use with the action. By default, the active caslib is used. Specify a value only if you need to access a table from a different caslib.

"computedOnDemand":True | False

when set to True, creates the computed variables when the table is loaded instead of when the action begins.

Alias	compOnDemand
Default	False

"computedVars":[{casinvardesc-1} <, {casinvardesc-2}, ...>]

specifies the names of the computed variables to create. Specify an expression for each variable in the computedVarsProgram parameter.

Alias

compVars

"format":"string"

specifies the format to apply to the variable.

"formattedLength":integer

specifies the length of format field plus the format precision.

"label":"string"

specifies the descriptive label for the variable.

* "name":"variable-name"

specifies the name for the variable.

"nfd":integer

specifies the length of the format precision.

"nfl":integer

specifies the length of the format field.

"computedVarsProgram":"string"

specifies an expression for each computed variable that you include in the computedVars parameter.

Alias

compPgm

"dataSourceOptions":{"key-1":{any-list-or-data-type-1} <, "key-2":{any-list-or-data-type-2}, ...>}

specifies data source options.

Alias

options, dataSource

"importOptions":{fileType="AUTO" | "BASESAS" | "CSV" | "DOCUMENT" | "DTA" | "ESP" | "EXCEL" | "FMT" | "HDAT" | "JMP" | "LASR" | "SPSS" | "XLS", fileType-specific-parameters}

specifies the settings for reading a table from a data source.

Alias

import_

The value that you specify for fileType determines the other parameters that apply. For more information about this common parameter, see importOptions (Appendix A: Common Parameters).

* "name":"table-name"

specifies the name of the table to use.

"onDemand":True | False

This parameter is deprecated.

Default

True

"singlePass":True | False

when set to True, does not create a transient table on the server. Setting this parameter to True can be efficient, but the data might not have stable ordering upon repeated runs.

Default

False

"vars":[{casinvardesc-1} <, {casinvardesc-2}, ...>]

specifies the variables to use in the action.

"format":"string"

specifies the format to apply to the variable.

"formattedLength":integer

specifies the length of format field plus the format precision.

"label":"string"

specifies the descriptive label for the variable.

* "name":"variable-name"

specifies the name for the variable.

"nfd":integer

specifies the length of the format precision.

"nfl":integer

specifies the length of the format field.

"where":"where-expression"

specifies an expression for subsetting the input data.

computeFeatures Action

Compute various features for audio files loaded into a Cloud Analytic Services table.

R Syntax

results <– cas.audio.computeFeatures(s,

audioColumn="string",

casOut=list(

caslib="string",

compress=TRUE | FALSE,

indexVars=list("variable-name-1" <, "variable-name-2", ...>),

label="string",

maxMemSize=64-bit-integer,

name="table-name",

onDemand=TRUE | FALSE,

promote=TRUE | FALSE,

replace=TRUE | FALSE,

replication=integer,

timeStamp="string",

where=list("string-1" <, "string-2", ...>)

copyVars=list("variable-name-1" <, "variable-name-2", ...>),

fbankOptions=list(

energyFloor=double,

rawEnergy=TRUE | FALSE,

useEnergy=TRUE | FALSE,

useLogFbank=TRUE | FALSE,

usePower=TRUE | FALSE

featureScalingMethod="NONE" | "STANDARDIZATION",

frameExtractionOptions=list(

blackmanCoeff=double,

dither=double,

frameLength=double,

frameShift=double,

preemphCoeff=double,

removeDcOffset=TRUE | FALSE,

roundToPowerOfTwo=TRUE | FALSE,

snipEdges=TRUE | FALSE,

windowType="BLACKMAN" | "HAMMING" | "HANNING" | "RECTANGULAR"

melBanksOptions=list(

highFreq=double,

lowFreq=double,

nBins=integer

mfccOptions=list(

cepstralLifter=double,

energyFloor=double,

nCeps=integer,

rawEnergy=TRUE | FALSE,

useEnergy=TRUE | FALSE

nContextFrames=integer,

nOutputFrames=integer,

plpOptions=list(

cepstralLifter=integer,

cepstralScale=double,

compressFactor=double,

energyFloor=double,

lpcOrder=integer,

nCeps=integer,

rawEnergy=TRUE | FALSE,

useEnergy=TRUE | FALSE

table=list(

caslib="string",

computedOnDemand=TRUE | FALSE,

computedVars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>),

computedVarsProgram="string",

dataSourceOptions=list(key-1=list(any-list-or-data-type-1) <, key-2=list(any-list-or-data-type-2), ...>),

name="table-name",

onDemand=TRUE | FALSE,

singlePass=TRUE | FALSE,

vars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>),

where="where-expression"

)

Parameter Descriptions

audioColumn="string"

specifies the name of the column in the input table containing the audio data

* casOut=list(casouttable)

specifies the settings for an output table.

For more information about specifying the casOut parameter, see the common casouttable parameter (Appendix A: Common Parameters).

copyVars=list("variable-name-1" <, "variable-name-2", ...>)

specifies the list of variables to transfer from the input table to the output table

Requirement

The specified values must be unique.

fbankOptions=list(fbankOptions)

specifies the settings used to determine how to perform the FBank feature computations

energyFloor=double

specifies the linear floor on energy (absolute, not relative) for the FBank feature computations

Default	0
Minimum value	0

rawEnergy=TRUE | FALSE

specifies that energy should be computed before preemphasis and windowing

Default

TRUE

useEnergy=TRUE | FALSE

specifies that an extra dimension containing the computed energy should be appended to each FBank feature frame

Default

FALSE

useLogFbank=TRUE | FALSE

specifies that the output should contain log-filterbank values (otherwise, the output values are linear)

Default

TRUE

usePower=TRUE | FALSE

specifies that power should be used in the FBank feature computations (otherwise, the magnitude is used)

Default

TRUE

featureScalingMethod="NONE" | "STANDARDIZATION"

specifies the feature scaling method to apply to the computed feature vectors

Default

NONE

specifies that no feature scaling method should be applied to the computed feature vectors

STANDARDIZATION

specifies that the set containing the same coefficient across all frames in an audio file should be scaled so that the resulting set has a mean of zero and unit variance

frameExtractionOptions=list(frameExtractionOptions)

specifies the settings used to determine how to break the audio file into frames

blackmanCoeff=double

specifies the constant coefficient used for the generalized Blackman window (this value is ignored for other window types)

Default

0.42

dither=double

specifies the dithering constant (0.0 means no dithering)

Default

frameLength=double

specifies the length of a frame (in milliseconds)

Default	25
Minimum value (exclusive)	0

frameShift=double

specifies the time difference (in milliseconds) between the beginnings of consecutive frames

Default	10
Minimum value (exclusive)	0

preemphCoeff=double

specifies the coefficient used in performing signal preemphasis

Default

0.97

removeDcOffset=TRUE | FALSE

specifies that the mean of the values in each frame should be subtracted from all values in that frame

Default

TRUE

roundToPowerOfTwo=TRUE | FALSE

specifies that the window size should be rounded to the next power of two

Default

TRUE

snipEdges=TRUE | FALSE

specifies that end effects should be handled by outputting only frames that completely fit the data

Default

TRUE

windowType="BLACKMAN" | "HAMMING" | "HANNING" | "RECTANGULAR"

specifies the type of window to apply to each frame upon extraction

Default

RECTANGULAR

BLACKMAN

specifies that a Blackman window should be applied when extracting frames

HAMMING

specifies that a Hamming window should be applied when extracting frames

HANNING

specifies that a Hanning window should be applied when extracting frames

RECTANGULAR

specifies that a rectangular window should be applied when extracting frames

melBanksOptions=list(melBanksOptions)

specifies the settings used to determine the mel-frequency banks

highFreq=double

specifies the high cutoff frequency for the mel-frequency bins (if negative, the value is added to the Nyquist frequency, which is determined from the sampling rate of the audio)

Default

lowFreq=double

specifies the low cutoff frequency for the mel-frequency bins

Default

nBins=integer

specifies the number of triangular mel-frequency bins

Default	23
Minimum value	1

mfccOptions=list(mfccOptions)

specifies the settings used to determine how to perform the MFCC feature computations

cepstralLifter=double

specifies the constant which controls the scaling of the MFCC feature values

Default

energyFloor=double

specifies the linear floor on energy (absolute, not relative) for the MFCC feature computations

Default	0
Minimum value	0

nCeps=integer

specifies the number of cepstral coefficients in each MFCC feature frame (including C0)

Default	13
Minimum value	1

rawEnergy=TRUE | FALSE

specifies that energy should be computed before preemphasis and windowing

Default

TRUE

useEnergy=TRUE | FALSE

specifies that energy (not C0) should be used in the MFCC feature computations

Default

TRUE

nContextFrames=integer

specifies the number of context frames to append before and after the current audio frame

Default	0
Minimum value	0

nOutputFrames=integer

specifies the exact number of frames to include in the output table (extra frames are dropped and missing frames are padded with zeros)

Minimum value

plpOptions=list(plpOptions)

specifies the settings used to determine how to perform the PLP feature computations

cepstralLifter=integer

specifies the constant which controls the scaling of the PLP feature values

Default

cepstralScale=double

specifies the cepstral scaling constant used in the PLP computation

Default	1
Minimum value (exclusive)	0

compressFactor=double

specifies the compression factor used in the PLP feature computations

Default	0.33333
Minimum value (exclusive)	0

energyFloor=double

specifies the linear floor on energy (absolute, not relative) for the PLP feature computations

Default	0
Minimum value	0

lpcOrder=integer

specifies the order of the linear predictive coding (LPC) analysis used in the PLP feature computations

Default	12
Minimum value	1

nCeps=integer

specifies the number of cepstral coefficients in each PLP feature frame (including C0)

Default	13
Minimum value	1

rawEnergy=TRUE | FALSE

specifies that energy should be computed before preemphasis and windowing

Default

TRUE

useEnergy=TRUE | FALSE

specifies that energy (not C0) should be used for the zeroth feature value in the PLP feature computations

Default

TRUE

* table=list(castable)

specifies the settings for an input table.

Long form	table=list(name="table-name")
Shortcut form	table="table-name"

The castable value can be one or more of the following:

caslib="string"

specifies the caslib that contains the table that you want to use with the action. By default, the active caslib is used. Specify a value only if you need to access a table from a different caslib.

computedOnDemand=TRUE | FALSE

when set to True, creates the computed variables when the table is loaded instead of when the action begins.

Alias	compOnDemand
Default	FALSE

computedVars=list( list(casinvardesc-1) <, list(casinvardesc-2), ...>)

specifies the names of the computed variables to create. Specify an expression for each variable in the computedVarsProgram parameter.

Alias

compVars

format="string"

specifies the format to apply to the variable.

formattedLength=integer

specifies the length of format field plus the format precision.

label="string"

specifies the descriptive label for the variable.

* name="variable-name"

specifies the name for the variable.

nfd=integer

specifies the length of the format precision.

nfl=integer

specifies the length of the format field.

computedVarsProgram="string"

specifies an expression for each computed variable that you include in the computedVars parameter.

Alias

compPgm

dataSourceOptions=list(key-1=list(any-list-or-data-type-1) <, key-2=list(any-list-or-data-type-2), ...>)

specifies data source options.

Alias

options, dataSource

importOptions=list(fileType="AUTO" | "BASESAS" | "CSV" | "DOCUMENT" | "DTA" | "ESP" | "EXCEL" | "FMT" | "HDAT" | "JMP" | "LASR" | "SPSS" | "XLS", fileType-specific-parameters)

specifies the settings for reading a table from a data source.

Alias

import

The value that you specify for fileType determines the other parameters that apply. For more information about this common parameter, see importOptions (Appendix A: Common Parameters).

* name="table-name"

specifies the name of the table to use.

onDemand=TRUE | FALSE

This parameter is deprecated.

Default

TRUE

singlePass=TRUE | FALSE

when set to True, does not create a transient table on the server. Setting this parameter to True can be efficient, but the data might not have stable ordering upon repeated runs.

Default

FALSE

vars=list( list(casinvardesc-1) <, list(casinvardesc-2), ...>)

specifies the variables to use in the action.

format="string"

specifies the format to apply to the variable.

formattedLength=integer

specifies the length of format field plus the format precision.

label="string"

specifies the descriptive label for the variable.

* name="variable-name"

specifies the name for the variable.

nfd=integer

specifies the length of the format precision.

nfl=integer

specifies the length of the format field.

where="where-expression"

specifies an expression for subsetting the input data.

Last updated: June 07, 2018