voicesdk::SpeechEndpointDetector Class Reference

Speech endpoint detector class (interface), intended to detect speech end in the audio stream. More...

#include <voicesdk/media/speech.h>

Public Types
using	Ptr = std::shared_ptr< SpeechEndpointDetector >

Public Member Functions
virtual void	reset ()=0
	Resets detector state.
virtual void	addSamples (const uint8_t *bytes, size_t bytesNum)=0
	Adds PCM16 audio samples to process. More...
virtual void	addSamples (const float *samples, size_t samplesNum)=0
	Adds float audio samples to process. More...
virtual void	addSamples (const int16_t *samples, size_t samplesNum)=0
	Adds PCM16 audio samples to process. More...
virtual bool	isSpeechEnded ()=0
	Returns detection state. More...

Static Public Member Functions
static SpeechEndpointDetector::Ptr	create (size_t minSpeechLengthMs, size_t maxSilenceLengthMs, size_t sampleRate)
	Factory method for creating SpeechEndpointDetector instance. More...

Detailed Description

Speech endpoint detector class (interface), intended to detect speech end in the audio stream.

Member Function Documentation

addSamples() [1/3]

virtual void voicesdk::SpeechEndpointDetector::addSamples ( const float *  samples, size_t  samplesNum  )

pure virtual

Adds float audio samples to process.

Parameters

samples	pointer to array containing normalized (from -1 to 1) float audio samples
samplesNum	size of array with samples

Exceptions

std::runtime_error	if runtime error occurred
voicesdk::LicenseException	if license error occurred

addSamples() [2/3]

virtual void voicesdk::SpeechEndpointDetector::addSamples ( const int16_t *  samples, size_t  samplesNum  )

pure virtual

Adds PCM16 audio samples to process.

Parameters

samples	pointer to array with samples
samplesNum	size of array with samples

Exceptions

std::runtime_error	if runtime error occurred
voicesdk::LicenseException	if license error occurred

addSamples() [3/3]

virtual void voicesdk::SpeechEndpointDetector::addSamples ( const uint8_t *  bytes, size_t  bytesNum  )

pure virtual

Adds PCM16 audio samples to process.

Parameters

bytes	pointer to array with samples
bytesNum	size of array with samples

Exceptions

std::runtime_error	if runtime error occurred
voicesdk::LicenseException	if license error occurred

create()

static SpeechEndpointDetector::Ptr voicesdk::SpeechEndpointDetector::create ( size_t  minSpeechLengthMs, size_t  maxSilenceLengthMs, size_t  sampleRate  )

static

Factory method for creating SpeechEndpointDetector instance.

Parameters

minSpeechLengthMs	minimum speech length required to begin speech end detection (ms)
maxSilenceLengthMs	silence after speech threshold used to determine if speech is already ended (ms)
sampleRate	input signal sampling rate

Returns

smart pointer to SpeechEndpointDetector instance

Exceptions

std::runtime_error	if runtime error occurred
voicesdk::LicenseException	if license error occurred

isSpeechEnded()

virtual bool voicesdk::SpeechEndpointDetector::isSpeechEnded ( )

pure virtual

Returns detection state.

Returns

true if speech end was detected, false otherwise