Yutou Technology (hangzhou) Co., Ltd.

Lichun Fan

Xin Liu

Peng Gao

Jiaqi Shi

Peng Cai

Mingjun Cai

The invention discloses a training method and a speech recognition method for a mixed frequency acoustic recognition model, which belongs to the technical field of speech recognition. The method comprises: obtaining a first-type speech feature of the first speech signal, and processing the first speech data to obtain corresponding first speech training data (S); obtaining the first-type speech feature of the second speech signal, and processing the second speech data to obtain corresponding second speech training data (S); obtaining a second-type speech feature of the first speech signal according to a power spectrum of the first speech signal, and obtaining the second-type speech feature of the second speech signal according to a power spectrum of the second speech signal (S); performing pre-training according to the first speech signal and the second speech signal, so as to form a preliminary recognition model of the hybrid frequency acoustic recognition model (S); and performing supervised parameter training on the preliminary recognition model according to the first speech training data, the second speech training data and the second-type speech feature, so as to form the hybrid frequency acoustic recognition model (S). The beneficial effects of the above technical solution are: the recognition model has better robustness and generalization.

Training method of hybrid frequency acoustic recognition model, and speech recognition method

Provided is a system for a robot to eliminate its own sound source, comprising a sound pickup unit () used for acquiring a digital signal having mixed left and right sound channels and outputting same; a sound-card driver unit () used for mixing the received reference signal of the robot sound source and the digital signal having mixed left and right sound channels, to form a mixed voice signal, and outputting same; a signal separation unit () used for separating the mixed voice signal into a digital signal having mixed left and right sound channels and a reference signal, and determining whether the digital signal having the mixed left and right sound channels contains an interference signal, obtaining a playback signal volume, and outputting same.

System for robot to eliminate own sound source

A robot voice direction-seeking turning system and method. The robot voice direction-seeking turning system employs a voice activity detection unit () that detects a received voice signal to determine whether or not a voice signal transmitted by a user (S) is present; a direction-seeking angle for the voice signal is calculated by a voice direction-seeking unit (), and a voice direction-seeking turning unit () is employed to drive a robot to turn towards the direction of the sound source of the voice signal on the basis of a direction-seeking angle (S). Employment of the robot voice direction-seeking turning method allows accurate acquisition of a valid voice signal transmitted by the user, thus increasing signal-to-noise ratio and the accuracy of voice recognition.

Growing community of inventors

Zhejiang, China

Lichun Fan