{"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/bi-directional-lattice-recurrent-neural","title":"Bi-Directional Lattice Recurrent Neural Networks for Confidence Estimation","arxiv_id":"1810.13024","date":"2018-10-30","proceeding":null,"authors":["Qiujia Li","Preben Ness","Anton Ragni","Mark Gales"],"abstract":"The standard approach to mitigate errors made by an automatic speech\nrecognition system is to use confidence scores associated with each predicted\nword. In the simplest case, these scores are word posterior probabilities\nwhilst more complex schemes utilise bi-directional recurrent neural network\n(BiRNN) models. A number of upstream and downstream applications, however, rely\non confidence scores assigned not only to 1-best hypotheses but to all words\nfound in confusion networks or lattices. These include but are not limited to\nspeaker adaptation, semi-supervised training and information retrieval.\nAlthough word posteriors could be used in those applications as confidence\nscores, they are known to have reliability issues. To make improved confidence\nscores more generally available, this paper shows how BiRNNs can be extended\nfrom 1-best sequences to confusion network and lattice structures. Experiments\nare conducted using one of the Cambridge University submissions to the IARPA\nOpenKWS 2016 competition. The results show that confusion network and\nlattice-based BiRNNs can provide a significant improvement in confidence\nestimation.","url_abs":"http://arxiv.org/abs/1810.13024v2","url_pdf":"http://arxiv.org/pdf/1810.13024v2.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":"bi-directional-lattice-recurrent-neural","repo_url":"https://github.com/qiujiali/lattice_rnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"bi-directional-lattice-recurrent-neural","repo_url":"https://github.com/alecokas/BiLatticeRNN-Confidence","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"bi-directional-lattice-recurrent-neural","repo_url":"https://github.com/alecokas/lattice_rnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"bi-directional-lattice-recurrent-neural","repo_url":"https://github.com/oliverrose1998/Attention-Confidence","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":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"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}