def use_cmvn(feat,cmvn,utt2spk=None,std=False,outFile=None):
'''
Apply CMVN statistics to feature.
Share Args:
Null
Parrallel Args:
<feat>: exkaldi feature or index table object.
<cmvn>: exkaldi CMVN statistics or index object.
<utt2spk>: file path or ListTable object.
<std>: If true,apply std normalization.
<outFile>: out file name.
Return:
feature or index table object.
'''
feats,cmvns,utt2spks,stds,outFiles = check_multiple_resources(feat,cmvn,utt2spk,std,outFile=outFile)
names = []
for i,feat,cmvn,utt2spk,std in zip(range(len(outFiles)),feats,cmvns,utt2spks,stds):
# verify feature and cmvn
declare.is_feature("feat",feat)
declare.is_cmvn("cmvn",cmvn)
# verify utt2spk
if utt2spk is not None:
declare.is_potential_list_table("utt2spk",utt2spk)
# std
declare.is_bool("std",std)
#stds[i] = "true" if std else "false"
names.append( f"cmvn({feat.name},{cmvn.name})" )
if utt2spks[0] is None:
cmdPattern = 'apply-cmvn --norm-vars={std} {cmvn} {feat} ark:{outFile}'
resources = {"feat":feats,"cmvn":cmvns,"std":stds,"outFile":outFiles}
else:
cmdPattern = 'apply-cmvn --norm-vars={std} --utt2spk=ark:{utt2spk} {cmvn} {feat} ark:{outFile}'
resources = {"feat":feats,"cmvn":cmvns,"utt2spk":utt2spks,"std":stds,"outFile":outFiles}
return run_kaldi_commands_parallel(resources,cmdPattern,analyzeResult=True,generateArchive="feat",archiveNames=names)
def __compute_feature(target,kaldiTool,useSuffix=None,name="feat",outFile=None):
'''
The base funtion to compute feature.
'''
declare.kaldi_existed()
if useSuffix != None:
declare.is_valid_string("useSuffix",useSuffix)
useSuffix = useSuffix.strip().lower()[-3:]
declare.is_instances("useSuffix",useSuffix,["scp","wav"])
else:
useSuffix = ""
targets,kaldiTools,useSuffixs,names,outFiles = check_multiple_resources(target,kaldiTool,useSuffix,name,outFile=outFile)
# pretreatment
fromSegment = False
with FileHandleManager() as fhm:
segments = []
for index,kaldiTool,target,useSuffix,name in zip(range(len(outFiles)),kaldiTools,targets,useSuffixs,names):
declare.is_classes("target",target,["str","ListTable","WavSegment"])
declare.is_valid_string("name",name)
if isinstance(target,str):
allFiles = list_files(target)
target = ListTable()
for filePath in allFiles:
filePath = filePath.strip()
if filePath[-4:].lower() == ".wav":
fileName = os.path.basename(filePath)
uttID = fileName[0:-4].replace(".","")
target[uttID] = filePath
elif filePath[-4:].lower() == '.scp':
target += load_list_table(filePath)
elif "wav" == useSuffix:
fileName = os.path.basename(filePath)
uttID = fileName.replace(".","")
target[uttID] = filePath
elif "scp" == useSuffix:
target += load_list_table(filePath)
else:
raise UnsupportedType('Unknown file suffix. You can declare whether <useSuffix> is "wav" or "scp".')
if len(target) == 0:
raise WrongDataFormat("There did not include any data to compute data in target.")
targets[index] = target
elif type_name(target) == "WavSegment":
segTemp = fhm.create("w+",suffix=".seg",encode="utf-8")
target.save(segTemp)
segments.append(segTemp.name)
targets[index] = target.detach_wav()
fromSegment = True
if fromSegment:
# define the command pattern
cmdPattern = "extract-segments scp:{wavFile} {segment} ark:- | {kaldiTool} ark:- ark:{outFile}"
# define resources
resources = {"wavFile":targets,"segment":segments,"kaldiTool":kaldiTools,"outFile":outFiles}
else:
# define the command pattern
cmdPattern = "{kaldiTool} scp:{wavFile} ark:{outFile}"
# define resources
resources = {"wavFile":targets,"kaldiTool":kaldiTools,"outFile":outFiles}
# Run
return run_kaldi_commands_parallel(resources,cmdPattern,analyzeResult=True,generateArchive="feat",archiveNames=names)
def compute_plp(target,rate=16000,frameWidth=25,frameShift=10,
melBins=23,featDim=13,windowType='povey',useSuffix=None,
config=None,name="plp",outFile=None):
'''
Compute PLP feature.
Share Args:
Null
Parallel Args:
<target>: wave file,scp file,exkaldi ListTable object or WavSegment object. If it is wave file,we will use it's file name as utterance ID.
<rate>: sample rate.
<frameWidth>: frame windows width (ms).
<frameShift>: shift windows width (ms).
<melbins>: the numbers of mel filter banks.
<featDim>: the output dinmensionality of PLP feature.
<windowType>: sample windows type.
<useSuffix>: If the suffix of file is not .scp and .wav,use this to specify it.
<config>: extra optional configurations.
<name>: the name of output feature object.
<outFile>: output file name.
Some usual options can be specified directly. If you want to use more,set <config> = your-configure.
You can use exkaldi.check_config('compute_plp') function to get the refereance of extra configurations.
Also you can run shell command "compute-plp-feats" to look their useage.
Return:
exkaldi feature or index table object.
'''
# check the basis configure parameters to build base commands
stdParameters = check_multiple_resources(rate,frameWidth,frameShift,melBins,featDim,windowType,config)
baseCmds = []
for rate,frameWidth,frameShift,melBins,featDim,windowType,config,_ in zip(*stdParameters):
declare.is_positive_int("rate",rate)
declare.is_positive_int("frameWidth",frameWidth)
declare.is_positive_int("frameShift",frameShift)
declare.is_positive_int("melBins",melBins)
declare.is_positive_int("featDim",featDim)
declare.greater_equal("frameWidth",frameWidth,"frameShift",frameShift)
declare.is_instances("windowType",windowType,["hamming","hanning","povey","rectangular","blackmann"])
kaldiTool = 'compute-plp-feats --allow-downsample --allow-upsample '
kaldiTool += f'--sample-frequency={rate} '
kaldiTool += f'--frame-length={frameWidth} '
kaldiTool += f'--frame-shift={frameShift} '
kaldiTool += f'--num-mel-bins={melBins} '
kaldiTool += f'--num-ceps={featDim} '
kaldiTool += f'--window-type={windowType} '
if config is not None:
if check_config(name='compute_plp',config=config):
for key,value in config.items():
if isinstance(value,bool):
if value is True:
kaldiTool += f"{key} "
else:
kaldiTool += f"{key}={value} "
baseCmds.append(kaldiTool)
# run the common function
return __compute_feature(target,baseCmds,useSuffix,name,outFile)