RPPT Tensor Operations - Audio Augmentations.

RPPT Tensor Operations - Audio Augmentations.#

RPP: RPPT Tensor Operations - Audio Augmentations.

RPPT Tensor Operations - Audio Augmentations. More...

Functions
RppStatus	rppt_non_silent_region_detection (RppPtr_t srcPtr, RpptDescPtr srcDescPtr, Rpp32s srcLengthTensor, Rpp32s detectedIndexTensor, Rpp32s *detectionLengthTensor, Rpp32f cutOffDB, Rpp32s windowLength, Rpp32f referencePower, Rpp32s resetInterval, rppHandle_t rppHandle, RppBackend executionBackend)
	Non Silent Region Detection augmentation on HIP/HOST backend. More...

RppStatus	rppt_to_decibels (RppPtr_t srcPtr, RpptDescPtr srcDescPtr, RppPtr_t dstPtr, RpptDescPtr dstDescPtr, RpptImagePatchPtr srcDims, Rpp32f cutOffDB, Rpp32f multiplier, Rpp32f referenceMagnitude, rppHandle_t rppHandle, RppBackend executionBackend)
	To Decibels augmentation on HIP/HOST backend. More...

RppStatus	rppt_pre_emphasis_filter (RppPtr_t srcPtr, RpptDescPtr srcDescPtr, RppPtr_t dstPtr, RpptDescPtr dstDescPtr, Rpp32s srcLengthTensor, Rpp32f coeffTensor, RpptAudioBorderType borderType, rppHandle_t rppHandle, RppBackend executionBackend)
	Pre Emphasis Filter augmentation on HIP/HOST backend. More...

RppStatus	rppt_down_mixing (RppPtr_t srcPtr, RpptDescPtr srcDescPtr, RppPtr_t dstPtr, RpptDescPtr dstDescPtr, Rpp32s *srcDimsTensor, bool normalizeWeights, rppHandle_t rppHandle, RppBackend executionBackend)
	Down Mixing augmentation on HIP/HOST backend. More...

RppStatus	rppt_spectrogram (RppPtr_t srcPtr, RpptDescPtr srcDescPtr, RppPtr_t dstPtr, RpptDescPtr dstDescPtr, Rpp32s srcLengthTensor, bool centerWindows, bool reflectPadding, Rpp32f windowFunction, Rpp32s nfft, Rpp32s power, Rpp32s windowLength, Rpp32s windowStep, rppHandle_t rppHandle, RppBackend executionBackend)
	Produces a spectrogram from a 1D audio buffer on HIP/HOST backend. More...

RppStatus	rppt_mel_filter_bank (RppPtr_t srcPtr, RpptDescPtr srcDescPtr, RppPtr_t dstPtr, RpptDescPtr dstDescPtr, Rpp32s *srcDims, Rpp32f maxFreq, Rpp32f minFreq, RpptMelScaleFormula melFormula, Rpp32s numFilter, Rpp32f sampleRate, bool normalize, rppHandle_t rppHandle, RppBackend executionBackend)
	Mel filter bank augmentation HIP/HOST backend. More...

RppStatus	rppt_resample (RppPtr_t srcPtr, RpptDescPtr srcDescPtr, RppPtr_t dstPtr, RpptDescPtr dstDescPtr, Rpp32f inRateTensor, Rpp32f outRateTensor, Rpp32s *srcDimsTensor, RpptResamplingWindow &window, rppHandle_t rppHandle, RppBackend executionBackend)
	Resample augmentation on HIP/HOST backend. More...

Detailed Description

RPPT Tensor Operations - Audio Augmentations.

Function Documentation

◆ rppt_down_mixing()

RppStatus rppt_down_mixing	(	RppPtr_t	srcPtr,
		RpptDescPtr	srcDescPtr,
		RppPtr_t	dstPtr,
		RpptDescPtr	dstDescPtr,
		Rpp32s *	srcDimsTensor,
		bool	normalizeWeights,
		rppHandle_t	rppHandle,
		RppBackend	executionBackend
	)

Down Mixing augmentation on HIP/HOST backend.

Down Mixing augmentation for audio data

Parameters

[in]	srcPtr	source tensor in HIP memory (for HIP backend) or HOST memory (for HOST backend)
[in]	srcDescPtr	source tensor descriptor (Restrictions - numDims = 2 or 3 (for single-channel or multi-channel audio tensor), offsetInBytes >= 0, dataType = F32)
[out]	dstPtr	destination tensor in HIP memory (for HIP backend) or HOST memory (for HOST backend)
[in]	dstDescPtr	destination tensor descriptor (Restrictions - numDims = 2, offsetInBytes >= 0, dataType = F32)
[in]	srcDimsTensor	source audio buffer length and number of channels (1D tensor in pinned memory (for HIP backend) or HOST memory (for HOST backend), of size batchSize * 2)
[in]	normalizeWeights	bool flag to specify if normalization of weights is needed
[in]	rppHandle	RPP HIP/HOST handle created with `rppCreate()`

Returns: A RppStatus enumeration.

Return values

RPP_SUCCESS	Successful completion.
RPP_ERROR*	Unsuccessful completion.

◆ rppt_mel_filter_bank()

RppStatus rppt_mel_filter_bank	(	RppPtr_t	srcPtr,
		RpptDescPtr	srcDescPtr,
		RppPtr_t	dstPtr,
		RpptDescPtr	dstDescPtr,
		Rpp32s *	srcDims,
		Rpp32f	maxFreq,
		Rpp32f	minFreq,
		RpptMelScaleFormula	melFormula,
		Rpp32s	numFilter,
		Rpp32f	sampleRate,
		bool	normalize,
		rppHandle_t	rppHandle,
		RppBackend	executionBackend
	)

Mel filter bank augmentation HIP/HOST backend.

Mel filter bank augmentation for audio data

Parameters

[in]	srcPtr	source tensor in HIP memory (for HIP backend) or HOST memory (for HOST backend)
[in]	srcDescPtr	source tensor descriptor (Restrictions - numDims = 3, offsetInBytes >= 0, dataType = F32, layout - NFT)
[out]	dstPtr	destination tensor in HIP memory (for HIP backend) or HOST memory (for HOST backend)
[in]	dstDescPtr	destination tensor descriptor (Restrictions - numDims = 3, offsetInBytes >= 0, dataType = F32, layout - NFT)
[in]	srcDimsTensor	source audio buffer length and number of channels (1D tensor in pinned memory (for HIP backend) or HOST memory (for HOST backend), of size batchSize * 2)
[in]	maxFreq	maximum frequency if not provided maxFreq = sampleRate / 2
[in]	minFreq	minimum frequency
[in]	melFormula	formula used to convert frequencies from hertz to mel and from mel to hertz (SLANEY / HTK)
[in]	numFilter	number of mel filters
[in]	sampleRate	sampling rate of the audio
[in]	normalize	boolean variable that determine whether to normalize weights / not
[in]	rppHandle	RPP HIP/HOST handle created with `rppCreate()`

Returns: A RppStatus enumeration.

Return values

RPP_SUCCESS	Successful completion.
RPP_ERROR*	Unsuccessful completion.

◆ rppt_non_silent_region_detection()

RppStatus rppt_non_silent_region_detection	(	RppPtr_t	srcPtr,
		RpptDescPtr	srcDescPtr,
		Rpp32s *	srcLengthTensor,
		Rpp32s *	detectedIndexTensor,
		Rpp32s *	detectionLengthTensor,
		Rpp32f	cutOffDB,
		Rpp32s	windowLength,
		Rpp32f	referencePower,
		Rpp32s	resetInterval,
		rppHandle_t	rppHandle,
		RppBackend	executionBackend
	)

Non Silent Region Detection augmentation on HIP/HOST backend.

Non Silent Region Detection augmentation for 1D audio buffer
Finds the starting index and length of non silent region in the audio buffer by comparing the calculated short-term power with cutoff value passed

Parameters

[in]	srcPtr	source tensor in HIP memory (for HIP backend) or HOST memory (for HOST backend)
[in]	srcDescPtr	source tensor descriptor (Restrictions - numDims = 2, offsetInBytes >= 0, dataType = F32)
[in]	srcLengthTensor	source audio buffer length (1D tensor in HIP memory (for HIP backend) or HOST memory (for HOST backend), of size batchSize)
[out]	detectedIndexTensor	beginning index of non silent region (1D tensor in pinned memory (for HIP backend) or HOST memory (for HOST backend), of size batchSize)
[out]	detectionLengthTensor	length of non silent region (1D tensor in pinned memory (for HIP backend) or HOST memory (for HOST backend), of size batchSize)
[in]	cutOffDB	cutOff in dB below which the signal is considered silent
[in]	windowLength	window length used for computing short-term power of the signal
[in]	referencePower	reference power that is used to convert the signal to dB
[in]	resetInterval	number of samples after which the moving mean average is recalculated to avoid precision loss
[in]	rppHandle	RPP HIP/HOST handle created with `rppCreate()`

Returns: A RppStatus enumeration.

Return values

RPP_SUCCESS	Successful completion.
RPP_ERROR*	Unsuccessful completion.

◆ rppt_pre_emphasis_filter()

RppStatus rppt_pre_emphasis_filter	(	RppPtr_t	srcPtr,
		RpptDescPtr	srcDescPtr,
		RppPtr_t	dstPtr,
		RpptDescPtr	dstDescPtr,
		Rpp32s *	srcLengthTensor,
		Rpp32f *	coeffTensor,
		RpptAudioBorderType	borderType,
		rppHandle_t	rppHandle,
		RppBackend	executionBackend
	)

Pre Emphasis Filter augmentation on HIP/HOST backend.

Pre Emphasis Filter augmentation for audio data

Parameters

[in]	srcPtr	source tensor in HIP memory (for HIP backend) or HOST memory (for HOST backend)
[in]	srcDescPtr	source tensor descriptor (Restrictions - numDims = 3, offsetInBytes >= 0, dataType = F32)
[out]	dstPtr	destination tensor in HIP memory (for HIP backend) or HOST memory (for HOST backend)
[in]	dstDescPtr	destination tensor descriptor (Restrictions - numDims = 3, offsetInBytes >= 0, dataType = F32)
[in]	srcLengthTensor	source audio buffer length (1D tensor in pinned memory (for HIP backend) or HOST memory (for HOST backend), of size batchSize)
[in]	coeffTensor	preemphasis coefficient (1D tensor in pinned memory (for HIP backend) or HOST memory (for HOST backend), of size batchSize)
[in]	borderType	border value policy
[in]	rppHandle	RPP HIP/HOST handle created with `rppCreate()`

Returns: A RppStatus enumeration.

Return values

RPP_SUCCESS	Successful completion.
RPP_ERROR*	Unsuccessful completion.

◆ rppt_resample()

RppStatus rppt_resample	(	RppPtr_t	srcPtr,
		RpptDescPtr	srcDescPtr,
		RppPtr_t	dstPtr,
		RpptDescPtr	dstDescPtr,
		Rpp32f *	inRateTensor,
		Rpp32f *	outRateTensor,
		Rpp32s *	srcDimsTensor,
		RpptResamplingWindow &	window,
		rppHandle_t	rppHandle,
		RppBackend	executionBackend
	)

Resample augmentation on HIP/HOST backend.

Resample augmentation for audio data

Parameters

[in]	srcPtr	source tensor in HIP memory (for HIP backend) or HOST memory (for HOST backend)
[in]	srcDescPtr	source tensor descriptor (Restrictions - numDims = 2 or 3 (for single-channel or multi-channel audio tensor), offsetInBytes >= 0, dataType = F32)
[out]	dstPtr	destination tensor in HIP memory (for HIP backend) or HOST memory (for HOST backend)
[in]	dstDescPtr	destination tensor descriptor (Restrictions - numDims = 2 or 3 (for single-channel or multi-channel audio tensor), offsetInBytes >= 0, dataType = F32)
[in]	inRate	Input sampling rate (1D tensor in pinned memory (for HIP backend) or HOST memory (for HOST backend), of size batchSize)
[in]	outRate	Output sampling rate (1D tensor in pinned memory (for HIP backend) or HOST memory (for HOST backend), of size batchSize)
[in]	srcDimsTensor	source audio buffer length and number of channels (1D tensor in pinned memory (for HIP backend) or HOST memory (for HOST backend), of size batchSize * 2)
[in]	window	Resampling window (struct of type RpptRpptResamplingWindow)
[in]	rppHandle	RPP HOST handle created with `rppCreate()`

Returns: A RppStatus enumeration.

Return values

RPP_SUCCESS	Successful completion.
RPP_ERROR*	Unsuccessful completion.

◆ rppt_spectrogram()

RppStatus rppt_spectrogram	(	RppPtr_t	srcPtr,
		RpptDescPtr	srcDescPtr,
		RppPtr_t	dstPtr,
		RpptDescPtr	dstDescPtr,
		Rpp32s *	srcLengthTensor,
		bool	centerWindows,
		bool	reflectPadding,
		Rpp32f *	windowFunction,
		Rpp32s	nfft,
		Rpp32s	power,
		Rpp32s	windowLength,
		Rpp32s	windowStep,
		rppHandle_t	rppHandle,
		RppBackend	executionBackend
	)

Produces a spectrogram from a 1D audio buffer on HIP/HOST backend.

Spectrogram for 1D audio buffer

Parameters

[in]	srcPtr	source tensor in HIP memory (for HIP backend) or HOST memory (for HOST backend)
[in]	srcDescPtr	source tensor descriptor (Restrictions - numDims = 2, offsetInBytes >= 0, dataType = F32)
[out]	dstPtr	destination tensor in HIP memory (for HIP backend) or HOST memory (for HOST backend)
[in]	dstDescPtr	destination tensor descriptor (Restrictions - numDims = 3, offsetInBytes >= 0, dataType = F32, layout - NFT / NTF)
[in]	srcLengthTensor	source audio buffer length (1D tensor in pinned memory (for HIP backend) or HOST memory (for HOST backend), of size batchSize)
[in]	centerWindows	indicates whether extracted windows should be padded so that the window function is centered at multiples of window_step
[in]	reflectPadding	indicates the padding policy when sampling outside the bounds of the signal
[in]	windowFunction	samples of the window function that will be multiplied to each extracted window when calculating the Short Time Fourier Transform (STFT). if windowFunction is a nullptr, then required windowFunction values will be generated inside the kernel
[in]	nfft	size of the FFT
[in]	power	exponent of the magnitude of the spectrum
[in]	windowLength	window size in number of samples
[in]	windowStep	step between the STFT windows in number of samples
[in]	rppHandle	RPP HIP/HOST handle created with `rppCreate()`

Returns: A RppStatus enumeration.

Return values

RPP_SUCCESS	Successful completion.
RPP_ERROR*	Unsuccessful completion.

◆ rppt_to_decibels()

RppStatus rppt_to_decibels	(	RppPtr_t	srcPtr,
		RpptDescPtr	srcDescPtr,
		RppPtr_t	dstPtr,
		RpptDescPtr	dstDescPtr,
		RpptImagePatchPtr	srcDims,
		Rpp32f	cutOffDB,
		Rpp32f	multiplier,
		Rpp32f	referenceMagnitude,
		rppHandle_t	rppHandle,
		RppBackend	executionBackend
	)

To Decibels augmentation on HIP/HOST backend.

To Decibels augmentation for 1D/2D audio buffer converts magnitude values to decibel values

Parameters

[in]	srcPtr	source tensor in HIP memory (for HIP backend) or HOST memory (for HOST backend)
[in]	srcDescPtr	source tensor descriptor (Restrictions - numDims = 2 or 3 (for single-channel or multi-channel/2D audio tensor with 1 channel), offsetInBytes >= 0, dataType = F32)
[out]	dstPtr	destination tensor in HIP memory (for HIP backend) or HOST memory (for HOST backend)
[in]	dstDescPtr	destination tensor descriptor (Restrictions - numDims = 2 or 3 (for single-channel or multi-channel/2D audio tensor with 1 channel), offsetInBytes >= 0, dataType = F32)
[in]	srcDims	source tensor sizes for each element in batch (2D tensor in pinned memory (for HIP backend) or HOST memory (for HOST backend), of size batchSize * 2)
[in]	cutOffDB	minimum or cut-off ratio in dB
[in]	multiplier	factor by which the logarithm is multiplied
[in]	referenceMagnitude	Reference magnitude if not provided maximum value of input used as reference
[in]	rppHandle	RPP HOST handle created with `rppCreate()`

Returns: A RppStatus enumeration.

Return values

RPP_SUCCESS	Successful completion.
RPP_ERROR*	Unsuccessful completion.

RPPT Tensor Operations - Audio Augmentations.

RPPT Tensor Operations - Audio Augmentations.#

Functions

Detailed Description

Function Documentation

◆ rppt_down_mixing()

◆ rppt_mel_filter_bank()

◆ rppt_non_silent_region_detection()

◆ rppt_pre_emphasis_filter()

◆ rppt_resample()

◆ rppt_spectrogram()

◆ rppt_to_decibels()