{"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/phoneme-bert-joint-language-modelling-of","title":"Phoneme-BERT: Joint Language Modelling of Phoneme Sequence and ASR Transcript","arxiv_id":"2102.00804","date":"2021-02-01","proceeding":null,"authors":["Mukuntha Narayanan Sundararaman","Ayush Kumar","Jithendra Vepa"],"abstract":"Recent years have witnessed significant improvement in ASR systems to recognize spoken utterances. However, it is still a challenging task for noisy and out-of-domain data, where substitution and deletion errors are prevalent in the transcribed text. These errors significantly degrade the performance of downstream tasks. In this work, we propose a BERT-style language model, referred to as PhonemeBERT, that learns a joint language model with phoneme sequence and ASR transcript to learn phonetic-aware representations that are robust to ASR errors. We show that PhonemeBERT can be used on downstream tasks using phoneme sequences as additional features, and also in low-resource setup where we only have ASR-transcripts for the downstream tasks with no phoneme information available. We evaluate our approach extensively by generating noisy data for three benchmark datasets - Stanford Sentiment Treebank, TREC and ATIS for sentiment, question and intent classification tasks respectively. The results of the proposed approach beats the state-of-the-art baselines comprehensively on each dataset.","url_abs":"https://arxiv.org/abs/2102.00804v2","url_pdf":"https://arxiv.org/pdf/2102.00804v2.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":"phoneme-bert-joint-language-modelling-of","repo_url":"https://github.com/Observeai-Research/Phoneme-BERT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"intent-classification","task_name":"Intent Classification"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"intent-classification-1","task_name":"intent-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2102.00804","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}