{"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/deep-recurrent-neural-networks-for-acoustic","title":"Deep Recurrent Neural Networks for Acoustic Modelling","arxiv_id":"1504.01482","date":"2015-04-07","proceeding":null,"authors":["William Chan","Ian Lane"],"abstract":"We present a novel deep Recurrent Neural Network (RNN) model for acoustic\nmodelling in Automatic Speech Recognition (ASR). We term our contribution as a\nTC-DNN-BLSTM-DNN model, the model combines a Deep Neural Network (DNN) with\nTime Convolution (TC), followed by a Bidirectional Long Short-Term Memory\n(BLSTM), and a final DNN. The first DNN acts as a feature processor to our\nmodel, the BLSTM then generates a context from the sequence acoustic signal,\nand the final DNN takes the context and models the posterior probabilities of\nthe acoustic states. We achieve a 3.47 WER on the Wall Street Journal (WSJ)\neval92 task or more than 8% relative improvement over the baseline DNN models.","url_abs":"http://arxiv.org/abs/1504.01482v1","url_pdf":"http://arxiv.org/pdf/1504.01482v1.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":[],"tasks":[{"task_slug":"acoustic-modelling","task_name":"Acoustic Modelling"},{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-wsj-eval92","task":"Speech Recognition","dataset":"WSJ eval92","model":"TC-DNN-BLSTM-DNN","rank_in_archive_order":11,"of":17,"metrics":{"Word Error Rate (WER)":"3.5"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}