{"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/joint-masked-cpc-and-ctc-training-for-asr","title":"Joint Masked CPC and CTC Training for ASR","arxiv_id":"2011.00093","date":"2020-10-30","proceeding":null,"authors":["Chaitanya Talnikar","Tatiana Likhomanenko","Ronan Collobert","Gabriel Synnaeve"],"abstract":"Self-supervised learning (SSL) has shown promise in learning representations of audio that are useful for automatic speech recognition (ASR). But, training SSL models like wav2vec~2.0 requires a two-stage pipeline. In this paper we demonstrate a single-stage training of ASR models that can utilize both unlabeled and labeled data. During training, we alternately minimize two losses: an unsupervised masked Contrastive Predictive Coding (CPC) loss and the supervised audio-to-text alignment loss Connectionist Temporal Classification (CTC). We show that this joint training method directly optimizes performance for the downstream ASR task using unsupervised data while achieving similar word error rates to wav2vec~2.0 on the Librispeech 100-hour dataset. Finally, we postulate that solving the contrastive task is a regularization for the supervised CTC loss.","url_abs":"https://arxiv.org/abs/2011.00093v2","url_pdf":"https://arxiv.org/pdf/2011.00093v2.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":"joint-masked-cpc-and-ctc-training-for-asr","repo_url":"https://github.com/facebookresearch/voxpopuli","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"contrastive-predictive-coding","method_name":"Contrastive Predictive Coding"},{"method_slug":"infonce","method_name":"InfoNCE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2011.00093","atlas_url":"https://app.syntology.ai/?focus=2011.00093","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}