A Highly Adaptive Acoustic Model for Accurate Multi-Dialect Speech Recognition

TL;DR

This paper introduces a highly adaptive, unified acoustic model for multi-dialect speech recognition that dynamically adjusts based on dialect information, significantly reducing word error rates across diverse dialects.

Contribution

A novel adaptive acoustic modeling technique that dynamically incorporates dialect information, enabling accurate recognition across multiple dialects with a single model.

Findings

Outperforms previous models in reducing WER by 8.11% relative.

Effective handling of unseen dialects with a simple training method.

Achieves superior accuracy on large-scale speech datasets.

Abstract

Despite the success of deep learning in speech recognition, multi-dialect speech recognition remains a difficult problem. Although dialect-specific acoustic models are known to perform well in general, they are not easy to maintain when dialect-specific data is scarce and the number of dialects for each language is large. Therefore, a single unified acoustic model (AM) that generalizes well for many dialects has been in demand. In this paper, we propose a novel acoustic modeling technique for accurate multi-dialect speech recognition with a single AM. Our proposed AM is dynamically adapted based on both dialect information and its internal representation, which results in a highly adaptive AM for handling multiple dialects simultaneously. We also propose a simple but effective training method to deal with unseen dialects. The experimental results on large scale speech datasets show that the proposed AM outperforms all the previous ones, reducing word error rates (WERs) by 8.11% relative compared to a single all-dialects AM and by 7.31% relative compared to dialect-specific AMs.