Meta-Whisper: Speech-Based Meta-ICL for ASR on Low-Resource Languages

Autor:	Hsu, Ming-Hao, Huang, Kuan Po, Lee, Hung-yi
Rok vydání:	2024
Předmět:	Electrical Engineering and Systems Science - Audio and Speech Processing Computer Science - Computation and Language Computer Science - Sound
Druh dokumentu:	Working Paper
Popis:	This paper presents Meta-Whisper, a novel approach to improve automatic speech recognition (ASR) for low-resource languages using the Whisper model. By leveraging Meta In-Context Learning (Meta-ICL) and a k-Nearest Neighbors (KNN) algorithm for sample selection, Meta-Whisper enhances Whisper's ability to recognize speech in unfamiliar languages without extensive fine-tuning. Experiments on the ML-SUPERB dataset show that Meta-Whisper significantly reduces the Character Error Rate (CER) for low-resource languages compared to the original Whisper model. This method offers a promising solution for developing more adaptable multilingual ASR systems, particularly for languages with limited resources.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2409.10429 Zobrazit plný text záznamu View this record from Arxiv