Unispeech-Sat: Universal Speech Representation Learning With Speaker Aware Pre-Training
Authors:
Top Cited Papers
- 23 May 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6152-6156
Abstract
Self-supervised learning (SSL) is a long-standing goal for speech processing, since it utilizes large-scale unlabeled data and avoids extensive human labeling. Recent years have witnessed great successes in applying self-supervised learning in speech recognition, while limited exploration was attempted in applying SSL for modeling speaker characteristics. In this paper, we aim to improve the existing SSL framework for speaker representation learning. Two methods are introduced for enhancing the unsupervised speaker information extraction. First, we apply multi-task learning to the current SSL framework, where we integrate utterance-wise contrastive loss with the SSL objective function. Second, for better speaker discrimination, we propose an utterance mixing strategy for data augmentation, where additional overlapped utterances are created unsupervisely and incorporated during training. We integrate the proposed methods into the HuBERT framework. Experiment results on the SUPERB benchmark show that the proposed system achieves state-of-the-art performance in universal representation learning, especially for speaker identification oriented tasks. An ablation study is performed verifying the efficacy of each proposed method. Finally, we scale up the training dataset to 94 thousand hours of public audio data and achieve further performance improvement in all SUPERB tasks.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- SUPERB: Speech Processing Universal PERformance Benchmark2021
- VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation2021
- Vector-Quantized Autoregressive Predictive Coding2020
- Libri-Light: A Benchmark for ASR with Limited or No Supervision2020
- Multi-Task Self-Supervised Learning for Robust Speech Recognition2020
- Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders2020
- Generative Pre-Training for Speech with Autoregressive Predictive Coding2020
- Unsupervised Pretraining Transfers Well Across Languages2020
- An Unsupervised Autoregressive Model for Speech Representation Learning2019
- wav2vec: Unsupervised Pre-Training for Speech Recognition2019