MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for Speech Recognition

TL;DR

MMSpeech introduces a multi-modal, multi-task encoder-decoder pre-training framework for Mandarin speech recognition, integrating speech, text, and phoneme data to improve recognition accuracy significantly.

Contribution

The paper presents a novel multi-task pre-training approach incorporating phoneme modality and self-supervised tasks, enhancing Mandarin ASR performance over existing methods.

Findings

Achieves state-of-the-art results on AISHELL-1

Over 40% relative improvement compared to previous pre-training methods

Effectively leverages unlabeled speech and text data for pre-training

Abstract

In this paper, we propose a novel multi-modal multi-task encoder-decoder pre-training framework (MMSpeech) for Mandarin automatic speech recognition (ASR), which employs both unlabeled speech and text data. The main difficulty in speech-text joint pre-training comes from the significant difference between speech and text modalities, especially for Mandarin speech and text. Unlike English and other languages with an alphabetic writing system, Mandarin uses an ideographic writing system where character and sound are not tightly mapped to one another. Therefore, we propose to introduce the phoneme modality into pre-training, which can help capture modality-invariant information between Mandarin speech and text. Specifically, we employ a multi-task learning framework including five self-supervised and supervised tasks with speech and text data. For end-to-end pre-training, we introduce self-supervised speech-to-pseudo-codes (S2C) and phoneme-to-text (P2T) tasks utilizing unlabeled speech and text data, where speech-pseudo-codes pairs and phoneme-text pairs are a supplement to the supervised speech-text pairs. To train the encoder to learn better speech representation, we introduce self-supervised masked speech prediction (MSP) and supervised phoneme prediction (PP) tasks to learn to map speech into phonemes. Besides, we directly add the downstream supervised speech-to-text (S2T) task into the pre-training process, which can further improve the pre-training performance and achieve better recognition results even without fine-tuning. Experiments on AISHELL-1 show that our proposed method achieves state-of-the-art performance, with a more than 40% relative improvement compared with other pre-training methods.