FIELD: information technology.
SUBSTANCE: method of detecting voice activity involves receiving a speech signal from a speech microphone; receiving a noise signal from a noise microphone different from the speech microphone; determining a speech characteristic value based at least in part on the speech signal, wherein determining the speech characteristic value comprises determining an absolute value of the autocorrelation of the speech signal; determining a combined characteristic value based at least in part on the speech signal and the noise signal, wherein determining the combined characteristic value comprises determining cross-correlation based on the speech signal and the noise signal; determining a voice activity metric based at least in part on one of the speech characteristic value and the combined characteristic value, and the ratio of the absolute value of the autocorrelation of the speech signal to the cross-correlation; and determining a voice activity state based on the voice activity metric.
EFFECT: high reliability of detecting voice activity.
22 cl, 9 dwg
Title | Year | Author | Number |
---|---|---|---|
AUDIO SIGNAL PROCESSING DEVICE AND METHOD | 2017 |
|
RU2725017C1 |
HIGHER SPEECH INTELLIGIBILITY WITH APPLICATION OF SEVERAL MICROPHONES ON SEVERAL DEVICES | 2009 |
|
RU2456701C2 |
INTELLIGENT GRADIENT NOISE REDUCTION SYSTEM | 2008 |
|
RU2461081C2 |
METHOD AND APPARATUS FOR CONTROLLING SMOOTHING OF STATIONARY BACKGROUND NOISE | 2008 |
|
RU2469419C2 |
NOISE-ROBUST SPEECH CODING MODE CLASSIFICATION | 2012 |
|
RU2584461C2 |
METHOD AND APPARATUS FOR DETECTING VOICE ACTIVITY | 2018 |
|
RU2768508C2 |
METHOD AND DEVICE TO DETECT VOICE ACTIVITY | 2013 |
|
RU2670785C9 |
METHOD AND DEVICE FOR TRANSMISSION OF SPEECH ACTIVITY IN DISTRIBUTION SYSTEM OF VOICE RECOGNITION | 2002 |
|
RU2291499C2 |
METHOD FOR REALIZING MACHINE ESTIMATION OF QUALITY OF SOUND SIGNALS | 2005 |
|
RU2312405C2 |
METHOD AND APPARATUS FOR ENCODING AND DECODING | 2009 |
|
RU2461898C2 |
Authors
Dates
2012-05-10—Published
2008-09-26—Filed