English

A practical framework for multi-domain speech recognition and an instance sampling method to neural language modeling

Audio and Speech Processing 2022-03-10 v1 Sound

Abstract

Automatic speech recognition (ASR) systems used on smart phones or vehicles are usually required to process speech queries from very different domains. In such situations, a vanilla ASR system usually fails to perform well on every domain. This paper proposes a multi-domain ASR framework for Tencent Map, a navigation app used on smart phones and in-vehicle infotainment systems. The proposed framework consists of three core parts: a basic ASR module to generate n-best lists of a speech query, a text classification module to determine which domain the speech query belongs to, and a reranking module to rescore n-best lists using domain-specific language models. In addition, an instance sampling based method to training neural network language models (NNLMs) is proposed to address the data imbalance problem in multi-domain ASR. In experiments, the proposed framework was evaluated on navigation domain and music domain, since navigating and playing music are two main features of Tencent Map. Compared to a general ASR system, the proposed framework achieves a relative 13% \sim 22% character error rate reduction on several test sets collected from Tencent Map and our in-car voice assistant.

Keywords

Cite

@article{arxiv.2203.04767,
  title  = {A practical framework for multi-domain speech recognition and an instance sampling method to neural language modeling},
  author = {Yike Zhang and Xiaobing Feng and Yi Liu and Songjun Cao and Long Ma},
  journal= {arXiv preprint arXiv:2203.04767},
  year   = {2022}
}

Comments

7 pages, 1 figure

R2 v1 2026-06-24T10:07:24.053Z