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_host (RppPtr_t srcPtr, RpptDescPtr srcDescPtr, Rpp32s srcLengthTensor, Rpp32s detectedIndexTensor, Rpp32s *detectionLengthTensor, Rpp32f cutOffDB, Rpp32s windowLength, Rpp32f referencePower, Rpp32s resetInterval, rppHandle_t rppHandle)
	Non Silent Region Detection augmentation on HOST backend. More...

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

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

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

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

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

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

RppStatus	rppt_spectrogram_host (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)
	Produces a spectrogram from a 1D audio buffer on HOST backend. More...

RppStatus	rppt_mel_filter_bank_host (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)
	Mel filter bank augmentation HOST backend. More...

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

Detailed Description

RPPT Tensor Operations - Audio Augmentations.

Function Documentation

◆ rppt_down_mixing_gpu()

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

Down Mixing augmentation on HIP backend.

Down Mixing augmentation for audio data

Parameters

[in]	srcPtr	source tensor in HIP memory
[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
[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 HIP/Pinned memory, of size batchSize * 2)
[in]	normalizeWeights	bool flag to specify if normalization of weights is needed
[in]	rppHandle	RPP HIP handle created with `rppCreateWithStreamAndBatchSize()`

Returns: A RppStatus enumeration.

Return values

RPP_SUCCESS	Successful completion.
RPP_ERROR*	Unsuccessful completion.

◆ rppt_down_mixing_host()

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

Down Mixing augmentation on HOST backend.

Down Mixing augmentation for audio data

Parameters

[in]	srcPtr	source tensor in HOST memory
[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 HOST memory
[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 HOST memory, of size batchSize * 2)
[in]	normalizeWeights	bool flag to specify if normalization of weights is needed
[in]	rppHandle	RPP HOST handle created with `rppCreateWithBatchSize()`

Returns: A RppStatus enumeration.

Return values

RPP_SUCCESS	Successful completion.
RPP_ERROR*	Unsuccessful completion.

◆ rppt_mel_filter_bank_host()

RppStatus rppt_mel_filter_bank_host	(	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
	)

Mel filter bank augmentation HOST backend.

Mel filter bank augmentation for audio data

Parameters

[in]	srcPtr	source tensor in HOST memory
[in]	srcDescPtr	source tensor descriptor (Restrictions - numDims = 3, offsetInBytes >= 0, dataType = F32, layout - NFT)
[out]	dstPtr	destination tensor in HOST memory
[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 HOST memory, 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 HOST handle created with `rppCreateWithBatchSize()`

Returns: A RppStatus enumeration.

Return values

RPP_SUCCESS	Successful completion.
RPP_ERROR*	Unsuccessful completion.

◆ rppt_non_silent_region_detection_gpu()

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

Non Silent Region Detection augmentation on HIP 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
[in]	srcDescPtr	source tensor descriptor (Restrictions - numDims = 3, offsetInBytes >= 0, dataType = F32)
[in]	srcLengthTensor	source audio buffer length (1D tensor in Pinned/HIP memory, of size batchSize)
[out]	detectedIndexTensor	beginning index of non silent region (1D tensor in Pinned/HIP memory, of size batchSize)
[out]	detectionLengthTensor	length of non silent region (1D tensor in Pinned/HIP memory, 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 handle created with `rppCreateWithStreamAndBatchSize()`

Returns: A RppStatus enumeration.

Return values

RPP_SUCCESS	Successful completion.
RPP_ERROR*	Unsuccessful completion.

◆ rppt_non_silent_region_detection_host()

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

Non Silent Region Detection augmentation on 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 HOST memory
[in]	srcDescPtr	source tensor descriptor (Restrictions - numDims = 3, offsetInBytes >= 0, dataType = F32)
[in]	srcLengthTensor	source audio buffer length (1D tensor in HOST memory, of size batchSize)
[out]	detectedIndexTensor	beginning index of non silent region (1D tensor in HOST memory, of size batchSize)
[out]	detectionLengthTensor	length of non silent region (1D tensor in HOST memory, 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 HOST handle created with `rppCreateWithBatchSize()`

Returns: A RppStatus enumeration.

Return values

RPP_SUCCESS	Successful completion.
RPP_ERROR*	Unsuccessful completion.

◆ rppt_pre_emphasis_filter_host()

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

Pre Emphasis Filter augmentation on HOST backend.

Pre Emphasis Filter augmentation for audio data

Parameters

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

Returns: A RppStatus enumeration.

Return values

RPP_SUCCESS	Successful completion.
RPP_ERROR*	Unsuccessful completion.

◆ rppt_resample_host()

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

Resample augmentation on HOST backend.

Resample augmentation for audio data

Parameters

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

Returns: A RppStatus enumeration.

Return values

RPP_SUCCESS	Successful completion.
RPP_ERROR*	Unsuccessful completion.

◆ rppt_spectrogram_host()

RppStatus rppt_spectrogram_host	(	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
	)

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

Spectrogram for 1D audio buffer

Parameters

[in]	srcPtr	source tensor in HOST memory
[in]	srcDescPtr	source tensor descriptor (Restrictions - numDims = 3, offsetInBytes >= 0, dataType = F32)
[out]	dstPtr	destination tensor in HOST memory
[in]	dstDescPtr	destination tensor descriptor (Restrictions - numDims = 3, offsetInBytes >= 0, dataType = F32, layout - NFT / NTF)
[in]	srcLengthTensor	source audio buffer length (1D tensor in HOST memory, 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)
[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 HOST handle created with `rppCreateWithBatchSize()`

Returns: A RppStatus enumeration.

Return values

RPP_SUCCESS	Successful completion.
RPP_ERROR*	Unsuccessful completion.

◆ rppt_to_decibels_gpu()

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

To Decibels augmentation on HIP backend.

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

Parameters

[in]	srcPtr	source tensor in HIP memory
[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
[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/HIP memory, 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 HIP handle created with `rppCreateWithStreamAndBatchSize()`

Returns: A RppStatus enumeration.

Return values

RPP_SUCCESS	Successful completion.
RPP_ERROR*	Unsuccessful completion.

◆ rppt_to_decibels_host()

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

To Decibels augmentation on HOST backend.

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

Parameters

[in]	srcPtr	source tensor in HOST memory
[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 HOST memory
[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 HOST memory, 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 `rppCreateWithBatchSize()`

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_gpu()

◆ rppt_down_mixing_host()

◆ rppt_mel_filter_bank_host()

◆ rppt_non_silent_region_detection_gpu()

◆ rppt_non_silent_region_detection_host()

◆ rppt_pre_emphasis_filter_host()

◆ rppt_resample_host()

◆ rppt_spectrogram_host()

◆ rppt_to_decibels_gpu()

◆ rppt_to_decibels_host()