Yutou Technology (hangzhou) Co., Ltd.

Fan Lichun

Peng Gao

Gao Peng

Zhu Lei

Meng Meng

The present invention relates to a microphone array based pickup method, comprising: performing voice activation detection using one channel voice signal among multichannel voice signals picked up and output by a microphone array, and determining if a voice activation signal occurs; locating the voice source by using the multichannel voice signals output by the microphone array to obtain the voice source locating direction; enhancing a voice signal in the voice source locating direction to obtain an enhanced voice signal; conducting voice wakeup detection on the enhanced voice signal and determining if a voice wakeup is detected; picking up and outputting the multichannel voice signals by the microphone array; Stepprocessing the multichannel voice signals picked up by the microphone array into one channel enhanced voice, and outputting the one channel enhanced voice as a finally picked up voice.

Microphone array based pickup method and system

The invention discloses a multi-language mixed speech recognition method, which belongs to the technical field of speech recognition; the method comprises: step S, configuring a multi-language mixed dictionary including a plurality of different languages; step S, performing training according to the multi-language mixed dictionary and multi-language speech data including a plurality of different languages to form an acoustic recognition model; step S, performing training according to multi-language text corpus including a plurality of different languages to form a language recognition model; step S, forming the speech recognition system by using the multi-language mixed dictionary, the acoustic recognition model and the language recognition model; and subsequently, recognizing mixed speech by using the speech recognition system, and outputting a corresponding recognition result. The above technical solution has the beneficial effects of being able to support the recognition of mixed speech in multiple languages, improving the accuracy and efficiency of recognition, and thus improving the performance of the speech recognition system.

Growing community of inventors

Hangzhou, China

Fan Lichun