{"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/decoar-2-0-deep-contextualized-acoustic","title":"DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization","arxiv_id":"2012.06659","date":"2020-12-11","proceeding":null,"authors":["Shaoshi Ling","Yuzong Liu"],"abstract":"Recent success in speech representation learning enables a new way to leverage unlabeled data to train speech recognition model. In speech representation learning, a large amount of unlabeled data is used in a self-supervised manner to learn a feature representation. Then a smaller amount of labeled data is used to train a downstream ASR system using the new feature representations. Based on our previous work DeCoAR and inspirations from other speech representation learning, we propose DeCoAR 2.0, a Deep Contextualized Acoustic Representation with vector quantization. We introduce several modifications over the DeCoAR: first, we use Transformers in encoding module instead of LSTMs; second, we introduce a vector quantization layer between encoder and reconstruction modules; third, we propose an objective that combines the reconstructive loss with vector quantization diversity loss to train speech representations. Our experiments show consistent improvements over other speech representations in different data-sparse scenarios. Without fine-tuning, a light-weight ASR model trained on 10 hours of LibriSpeech labeled data with DeCoAR 2.0 features outperforms the model trained on the full 960-hour dataset with filterbank features.","url_abs":"https://arxiv.org/abs/2012.06659v1","url_pdf":"https://arxiv.org/pdf/2012.06659v1.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":"decoar-2-0-deep-contextualized-acoustic","repo_url":"https://github.com/awslabs/speech-representations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"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=2012.06659","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}