Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter

TL;DR

This paper introduces two parameter-efficient methods, language prompt tuning and frame-level language adapter, to improve multilingual speech recognition performance across multiple languages, and explores their integration.

Contribution

It proposes novel, lightweight techniques for enhancing multilingual speech recognition and investigates their combined effectiveness.

Findings

Significant performance improvements across seven languages.

Effective integration of language prompt tuning and frame-level language adapter.

Parameter-efficient methods outperform baseline models.

Abstract

Multilingual intelligent assistants, such as ChatGPT, have recently gained popularity. To further expand the applications of multilingual artificial intelligence assistants and facilitate international communication, it is essential to enhance the performance of multilingual speech recognition, which is a crucial component of speech interaction. In this paper, we propose two simple and parameter-efficient methods: language prompt tuning and frame-level language adapter, to respectively enhance language-configurable and language-agnostic multilingual speech recognition. Additionally, we explore the feasibility of integrating these two approaches using parameter-efficient fine-tuning methods. Our experiments demonstrate significant performance improvements across seven languages using our proposed methods.