Method and apparatus for detecting a voice activity in an input audio signal
AssigneeHuawei Technologies Co., Ltd.
InventorZhe Wang
Life of this patent
Estimating the term…
Abstract
The disclosure provides a method and an apparatus for detecting a voice activity in an input audio signal composed of frames. A noise attribute of the input signal is determined based on a received frame of the input audio signal. A voice activity detection (VAD) parameter is derived based on the noise attribute of the input audio signal using an adaptive function. The derived VAD parameter is compared with a threshold value to provide a voice activity detection decision. The input audio signal is processed according to the voice activity detection decision.
Claims19
A method for detecting a voice activity in an input audio signal for use by a voice signal encoder, wherein the input audio signal is composed of frames, the method comprising:
- determining a noise attribute of the input audio signal based on a received frame of the input audio signal;
- dividing the received frame of the input audio signal into one or more frequency sub-bands;
- obtaining a signal to noise ratio for each of the one or more frequency sub-bands;
- calculating a sub-band specific parameter of each frequency sub-band based on the signal to noise ratio of the frequency sub-band using an adaptive function, wherein at least one parameter of the adaptive function is selected based on the noise attribute of the input audio signal;
- deriving a modified segmental signal to noise ratio as a voice activity detection (VAD) parameter by summing up the calculated sub-band specific parameter of each frequency sub-band;
- and
- comparing the VAD parameter with a threshold value to provide a voice activity detection decision (VADD).
A voice encoder, comprising a receiver and a memory storing program codes for execution by a processor, wherein:
- the receiver is configured to receive at least one frame of an input audio signal;
- and
- the program codes comprise instructions for:
- determining a noise attribute of the input audio signal based on the received frame of the input audio signal,
- dividing the received frame of the input audio signal into one or more frequency sub-bands,
- obtaining a signal to noise ratio for each of the one or more frequency sub-bands,
- calculating a sub-band specific parameter of each frequency sub-band based on the signal to noise ratio of the frequency sub-band using an adaptive function, wherein at least one parameter of the adaptive function is selected based on the noise attribute of the input audio signal,
- deriving a modified segmental signal to noise ratio as a voice activity detection (VAD) parameter by summing up the sub-band specific parameter of frequency each sub-band, and
- comparing the VAD parameter with a threshold value to provide a voice activity detection decision (VADD).
Dependencies are inferred from the claim text.