From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition

Abstract

In this work, we propose a new parameter-efficient learning framework based on neural model reprogramming for cross-lingual speech recognition, which can \textbf{re-purpose} well-trained English automatic speech recognition (ASR) models to recognize the other languages. We design different auxiliary neural architectures focusing on learnable pre-trained feature enhancement that, for the first time, empowers model reprogramming on ASR. Specifically, we investigate how to select trainable components (i.e., encoder) of a conformer-based RNN-Transducer, as a frozen pre-trained backbone. Experiments on a seven-language multilingual LibriSpeech speech (MLS) task show that model reprogramming only requires 4.2% (11M out of 270M) to 6.8% (45M out of 660M) of its original trainable parameters from a full ASR model to perform competitive results in a range of 11.9% to 8.1% WER averaged across different languages. In addition, we discover different setups to make large-scale pre-trained ASR succeed in both monolingual and multilingual speech recognition. Our methods outperform existing ASR tuning architectures and their extension with self-supervised losses (e.g., w2v-bert) in terms of lower WER and better training efficiency.

arXiv commentSubmitted to ICASSP 2023. The project was initiated in May 2022 during a research internship at Google Research

References in corpus (7)

• Sequence Transduction with Recurrent Neural Networks
• Libri-Light: A Benchmark for ASR with Limited or No Supervision
• MLS: A Large-Scale Multilingual Dataset for Speech Research
• Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling
• BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition
• Learning Hidden Unit Contributions for Unsupervised Acoustic Model Adaptation
• Towards Better Domain Adaptation for Self-supervised Models: A Case Study of Child ASR

Cited by in corpus (6)

• Low-rank Adaptation of Large Language Model Rescoring for Parameter-Efficient Speech Recognition
• Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition
• A Parameter-Efficient Learning Approach to Arabic Dialect Identification with Pre-Trained General-Purpose Speech Model
• Parameter-Efficient Learning for Text-to-Speech Accent Adaptation
• How to Estimate Model Transferability of Pre-Trained Speech Models?
• Differentially Private Adapters for Parameter Efficient Acoustic Modeling