Tencent Technology (shenzhen) Company Limited

Tencent Technology Company Limited

Yanmin Qian

Dong Yu

Dong Hai Yu

Dan Su

Meng Yu

Lianwu Chen

A multi-person speech separation method is provided for a terminal. The method includes extracting a hybrid speech feature from a hybrid speech signal requiring separation, N human voices being mixed in the hybrid speech signal, N being a positive integer greater than or equal to 2; extracting a masking coefficient of the hybrid speech feature by using a generative adversarial network (GAN) model, to obtain a masking matrix corresponding to the N human voices, wherein the GAN model comprises a generative network model and an adversarial network model; and performing a speech separation on the masking matrix corresponding to the N human voices and the hybrid speech signal by using the GAN model, and outputting N separated speech signals corresponding to the N human voices.

Multi-person speech separation method and apparatus using a generative adversarial network model

Provided are a speech recognition training processing method and an apparatus including the same. The speech recognition training processing method includes acquiring a stream of speech data from one or more speakers, extracting an auxiliary feature corresponding to a speech characteristic of the one or more speaker and updating an acoustic model by performing permutation invariant training (PIT) model training based on the auxiliary feature.

Adaptive permutation invariant training with auxiliary information for monaural multi-talker speech recognition

Provided are a speech recognition training processing method and an apparatus including the same. The speech recognition training processing method includes acquiring a multi-talker mixed speech signal from a plurality of speakers, performing permutation invariant training (PIT) model training on the multi-talker mixed speech signal based on knowledge from a single-talker speech recognition model and updating a multi-talker speech recognition model based on a result of the PIT model training.

Knowledge transfer in permutation invariant training for single-channel multi-talker speech recognition

Provided are a speech recognition training processing method and an apparatus including the same. The speech recognition training processing method includes acquiring multi-talker mixed speech sequence data corresponding to a plurality of speakers, encoding the multi-speaker mixed speech sequence data into an embedded sequence data, generating speaker specific context vectors at each frame based on the embedded sequence, generating senone posteriors for each of the speaker based on the speaker specific context vectors and updating an acoustic model by performing permutation invariant training (PIT) model training based on the senone posteriors.

Growing community of inventors

Shanghai, China

Yanmin Qian