Tencent Technology (Shenzhen) Company Limited (20240404516). AUDIO PROCESSING METHOD AND RELATED APPARATUS

AUDIO PROCESSING METHOD AND RELATED APPARATUS

Organization Name

Tencent Technology (Shenzhen) Company Limited

Inventor(s)

Zhanheng Yang of Shenzhen (CN)

Sining Sun of Shenzhen (CN)

AUDIO PROCESSING METHOD AND RELATED APPARATUS

This abstract first appeared for US patent application 20240404516 titled 'AUDIO PROCESSING METHOD AND RELATED APPARATUS

Original Abstract Submitted

an audio processing method includes: acquiring an audio signal including audio frames; inputting the audio frames into a streaming acoustic network to obtain phoneme features representing phoneme information of the audio signal and streaming audio features; acquiring an entity set including first entities, wherein the first entities correspond to pieces of phoneme information; extracting second entities from the entity set based on the phoneme features, wherein the second entities correspond to the phoneme features, and wherein a second number of the second entities is greater than or equal to a third number of the audio frames and less than or equal to a first number of the first entities; obtaining a text recognition result based on inputting the audio signal, the streaming audio features, and the second entities into a non-streaming acoustic network; and outputting the text recognition result.