Weakly-supervised Speech Pre-training: A Case Study On Target Speech Recognition
2023 · Wangyou Zhang, Yanmin Qian
Abstract
Self-supervised learning (SSL) based speech pre-training has attracted much attention for its capability of extracting rich representations learned from massive unlabeled data. On the other hand, the use of weakly-supervised data is less explored for speech pre-training. To fill this gap, we propose a weakly-supervised speech pre-training method based on speaker-aware speech data. It adopts a similar training procedure to the widely-used masked speech prediction based SSL framework, while incorporating additional target-speaker enrollment information as an auxiliary input. In this way, the learned representation is steered towards the target speaker even in the presence of highly overlapping interference, allowing potential applications to tasks such as target speech recognition. Our experiments on Libri2Mix and WSJ0-2mix datasets show that the proposed model achieves significantly better ASR performance compared to WavLM, the state-of-the-art SSL model with denoising capability.
Authors
(none)
Tags
Stats
Related papers
- Unispeech-sat: Universal Speech Representation Learning With Speaker Aware Pre-training (2021)0.00
- Analyzing The Factors Affecting Usefulness Of Self-supervised Pre-trained Representations For Speech Recognition (2022)0.00
- Feature Learning And Ensemble Pre-tasks Based Self-supervised Speech Denoising And Dereverberation (2022)0.00
- An Adapter Based Pre-training For Efficient And Scalable Self-supervised Speech Representation Learning (2021)8.35
- Self-supervised Learning For Speech Recognition With Intermediate Layer Supervision (2021)9.41
- Deploying Self-supervised Learning In The Wild For Hybrid Automatic Speech Recognition (2022)0.00
- Adapting Self-supervised Models To Multi-talker Speech Recognition Using Speaker Embeddings (2022)10.61
- Investigating Self-supervised Learning For Speech Enhancement And Separation (2022)13.44