The reviewed record of science sign in
Pith

arxiv: 2412.16474 · v1 · pith:RF4SEKJJ · submitted 2024-12-21 · eess.AS · cs.CL

Enhancing Multilingual ASR for Unseen Languages via Language Embedding Modeling

Reviewed by Pithpith:RF4SEKJJopen to challenge →

classification eess.AS cs.CL
keywords languagesunseenlanguageembeddingmultilingualweightedwhispermethods
0
0 comments X
read the original abstract

Multilingual Automatic Speech Recognition (ASR) aims to recognize and transcribe speech from multiple languages within a single system. Whisper, one of the most advanced ASR models, excels in this domain by handling 99 languages effectively, leveraging a vast amount of data and incorporating language tags as prefixes to guide the recognition process. However, despite its success, Whisper struggles with unseen languages, those not included in its pre-training. Motivated by the observation that many languages share linguistic characteristics, we propose methods that exploit these relationships to enhance ASR performance on unseen languages. Specifically, we introduce a weighted sum method, which computes a weighted sum of the embeddings of language tags, using Whisper's predicted language probabilities. In addition, we develop a predictor-based approach that refines the weighted sum embedding to more closely approximate the true embedding for unseen languages. Experimental results demonstrate substantial improvements in ASR performance, both in zero-shot and fine-tuning settings. Our proposed methods outperform baseline approaches, providing an effective solution for addressing unseen languages in multilingual ASR.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.