Meta Learning For End-to-end Low-resource Speech Recognition

Abstract

In this paper, we proposed to apply meta learning approach for low-resource automatic speech recognition (ASR). We formulated ASR for different languages as different tasks, and meta-learned the initialization parameters from many pretraining languages to achieve fast adaptation on unseen target language, via recently proposed model-agnostic meta learning algorithm (MAML). We evaluated the proposed approach using six languages as pretraining tasks and four languages as target tasks. Preliminary results showed that the proposed method, MetaASR, significantly outperforms the state-of-the-art multitask pretraining approach on all target languages with different combinations of pretraining languages. In addition, since MAML's model-agnostic property, this paper also opens new research direction of applying meta learning to more speech-related applications.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhsu2019meta

Related papers

• SMILE: Speech Meta In-context Learning For Low-resource Language Automatic Speech Recognition (2024)0.00
• Adaptive Activation Network For Low Resource Multilingual Speech Recognition (2022)0.00
• Transfer Learning Of Language-independent End-to-end ASR With Language Model Fusion (2018)0.00
• Improved End-to-end Dysarthric Speech Recognition Via Meta-learning Based Model Re-initialization (2020)10.48
• Data Efficient Direct Speech-to-text Translation With Modality Agnostic Meta-learning (2019)0.00
• Learning Cross-lingual Mappings For Data Augmentation To Improve Low-resource Speech Recognition (2023)0.00
• Parameter-efficient Adaptation Of Multilingual Multimodal Models For Low-resource ASR (2024)2.26
• Language-agnostic Meta-learning For Low-resource Text-to-speech With Articulatory Features (2022)9.76