Adaptive Contextual Biasing for Transducer Based Streaming Speech Recognition

Tianyi Xu, Zhanheng Yang, Kaixun Huang, Pengcheng Guo, Ao Zhang, Biao Li, Changru Chen, Chao Li, Lei Xie

科研成果: 期刊稿件会议文章同行评审

8 引用 (Scopus)

摘要

By incorporating additional contextual information, deep biasing methods have emerged as a promising solution for speech recognition of personalized words. However, for real-world voice assistants, always biasing on such personalized words with high prediction scores can significantly degrade the performance of recognizing common words. To address this issue, we propose an adaptive contextual biasing method based on Context-Aware Transformer Transducer (CATT) that utilizes the biased encoder and predictor embeddings to perform streaming prediction of contextual phrase occurrences. Such prediction is then used to dynamically switch the bias list on and off, enabling the model to adapt to both personalized and common scenarios. Experiments on Librispeech and internal voice assistant datasets show that our approach can achieve up to 6.7% and 20.7% relative reduction in WER and CER compared to the baseline respectively, mitigating up to 96.7% and 84.9% of the relative WER and CER increase for common cases. Furthermore, our approach has a minimal performance impact in personalized scenarios while maintaining a streaming inference pipeline with negligible RTF increase.

源语言英语
页(从-至)1668-1672
页数5
期刊Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
2023-August
DOI
出版状态已出版 - 2023
活动24th International Speech Communication Association, Interspeech 2023 - Dublin, 爱尔兰
期限: 20 8月 202324 8月 2023

指纹

探究 'Adaptive Contextual Biasing for Transducer Based Streaming Speech Recognition' 的科研主题。它们共同构成独一无二的指纹。

引用此