{"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/character-level-incremental-speech","title":"Character-Level Incremental Speech Recognition with Recurrent Neural Networks","arxiv_id":"1601.06581","date":"2016-01-25","proceeding":null,"authors":["Kyuyeon Hwang","Wonyong Sung"],"abstract":"In real-time speech recognition applications, the latency is an important\nissue. We have developed a character-level incremental speech recognition (ISR)\nsystem that responds quickly even during the speech, where the hypotheses are\ngradually improved while the speaking proceeds. The algorithm employs a\nspeech-to-character unidirectional recurrent neural network (RNN), which is\nend-to-end trained with connectionist temporal classification (CTC), and an\nRNN-based character-level language model (LM). The output values of the\nCTC-trained RNN are character-level probabilities, which are processed by beam\nsearch decoding. The RNN LM augments the decoding by providing long-term\ndependency information. We propose tree-based online beam search with\nadditional depth-pruning, which enables the system to process infinitely long\ninput speech with low latency. This system not only responds quickly on speech\nbut also can dictate out-of-vocabulary (OOV) words according to pronunciation.\nThe proposed model achieves the word error rate (WER) of 8.90% on the Wall\nStreet Journal (WSJ) Nov'92 20K evaluation set when trained on the WSJ SI-284\ntraining set.","url_abs":"http://arxiv.org/abs/1601.06581v2","url_pdf":"http://arxiv.org/pdf/1601.06581v2.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":"character-level-incremental-speech","repo_url":"https://github.com/nikhilrathaur/Handwriting-to-Digital-Text","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}