{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/unispeech-sat-universal-speech-representation","title":"UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training","arxiv_id":"2110.05752","date":"2021-10-12","proceeding":null,"authors":["Sanyuan Chen","Yu Wu","Chengyi Wang","Zhengyang Chen","Zhuo Chen","Shujie Liu","Jian Wu","Yao Qian","Furu Wei","Jinyu Li","Xiangzhan Yu"],"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 witness 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 the multi-task learning to the current SSL framework, where we integrate the 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 incorporate during training. We integrate the proposed methods into the HuBERT framework. Experiment results on 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 training dataset to 94 thousand hours public audio data and achieve further performance improvement in all SUPERB tasks.","url_abs":"https://arxiv.org/abs/2110.05752v1","url_pdf":"https://arxiv.org/pdf/2110.05752v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"unispeech-sat-universal-speech-representation","repo_url":"https://github.com/microsoft/unispeech","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"unispeech-sat-universal-speech-representation","repo_url":"https://github.com/cywang97/unispeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"unispeech-sat-universal-speech-representation","repo_url":"https://github.com/sanyuan-chen/unispeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"unispeech-sat-universal-speech-representation","repo_url":"https://github.com/MindCode-4/code-1/tree/main/unispeech_sat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"unispeech-sat-universal-speech-representation","repo_url":"https://github.com/MindCode-4/code-5/tree/main/unispeech_sat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"speaker-identification","task_name":"Speaker Identification"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-representation-learning","task_name":"Speech Representation Learning"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.05752","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}