Call Center SDK
1.11.3
|
Speech endpoint detector class (interface), intended to detect speech end in the Opus audio stream. More...
#include <voicesdk/media/speech.h>
Public Types | |
using | Ptr = std::shared_ptr< SpeechEndpointDetectorOpus > |
Public Member Functions | |
virtual void | reset ()=0 |
Resets detector state. | |
virtual void | addPacket (const uint8_t *bytes, size_t bytesNum)=0 |
Adds Opus packet to process. More... | |
virtual bool | isSpeechEnded ()=0 |
Returns detection state. More... | |
Static Public Member Functions | |
static SpeechEndpointDetectorOpus::Ptr | create (size_t minSpeechLengthMs, size_t maxSilenceLengthMs, size_t sampleRate) |
Factory method for creating SpeechEndpointDetectorOpus instance. More... | |
Speech endpoint detector class (interface), intended to detect speech end in the Opus audio stream.
|
pure virtual |
Adds Opus packet to process.
bytes | A buffer containing single Opus packet. It is expected that packet contains data for single mono stream |
bytesNum | Number of bytes |
std::runtime_error | if runtime error occurred |
voicesdk::LicenseException | if license error occurred |
|
static |
Factory method for creating SpeechEndpointDetectorOpus instance.
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 |
std::runtime_error | if runtime error occurred |
voicesdk::LicenseException | if license error occurred |
|
pure virtual |
Returns detection state.