{"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/transformer-based-multi-aspect-multi","title":"Transformer-Based Multi-Aspect Multi-Granularity Non-Native English Speaker Pronunciation Assessment","arxiv_id":"2205.03432","date":"2022-05-06","proceeding":null,"authors":["Yuan Gong","Ziyi Chen","Iek-Heng Chu","Peng Chang","James Glass"],"abstract":"Automatic pronunciation assessment is an important technology to help self-directed language learners. While pronunciation quality has multiple aspects including accuracy, fluency, completeness, and prosody, previous efforts typically only model one aspect (e.g., accuracy) at one granularity (e.g., at the phoneme-level). In this work, we explore modeling multi-aspect pronunciation assessment at multiple granularities. Specifically, we train a Goodness Of Pronunciation feature-based Transformer (GOPT) with multi-task learning. Experiments show that GOPT achieves the best results on speechocean762 with a public automatic speech recognition (ASR) acoustic model trained on Librispeech.","url_abs":"https://arxiv.org/abs/2205.03432v1","url_pdf":"https://arxiv.org/pdf/2205.03432v1.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":"transformer-based-multi-aspect-multi","repo_url":"https://github.com/YuanGongND/gopt","is_official":1,"mentioned_in_paper":1,"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":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"phone-level-pronunciation-scoring","task_name":"Phone-level pronunciation scoring"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"utterance-level-pronounciation-scoring","task_name":"Utterance-level pronounciation scoring"},{"task_slug":"word-level-pronunciation-scoring","task_name":"Word-level pronunciation scoring"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/phone-level-pronunciation-scoring-on","task":"Phone-level pronunciation scoring","dataset":"speechocean762","model":"GOPT-PAII","rank_in_archive_order":3,"of":8,"metrics":{"Pearson correlation coefficient (PCC)":"0.68"},"uses_additional_data":true},{"leaderboard":"/sota/phone-level-pronunciation-scoring-on","task":"Phone-level pronunciation scoring","dataset":"speechocean762","model":"GOPT-Librispeech","rank_in_archive_order":7,"of":8,"metrics":{"Pearson correlation coefficient (PCC)":"0.61"},"uses_additional_data":false},{"leaderboard":"/sota/utterance-level-pronounciation-scoring-on","task":"Utterance-level pronounciation scoring","dataset":"speechocean762","model":"GOPT-Librispeech","rank_in_archive_order":4,"of":5,"metrics":{"Pearson correlation coefficient (PCC)":"0.74"},"uses_additional_data":false},{"leaderboard":"/sota/utterance-level-pronounciation-scoring-on","task":"Utterance-level pronounciation scoring","dataset":"speechocean762","model":"GOPT-PAII","rank_in_archive_order":5,"of":5,"metrics":{"Pearson correlation coefficient (PCC)":"0.73"},"uses_additional_data":true},{"leaderboard":"/sota/word-level-pronunciation-scoring-on","task":"Word-level pronunciation scoring","dataset":"speechocean762","model":"GOPT-PAII","rank_in_archive_order":3,"of":5,"metrics":{"Pearson correlation coefficient (PCC)":"0.60"},"uses_additional_data":true},{"leaderboard":"/sota/word-level-pronunciation-scoring-on","task":"Word-level pronunciation scoring","dataset":"speechocean762","model":"GOPT-Librispeech","rank_in_archive_order":5,"of":5,"metrics":{"Pearson correlation coefficient (PCC)":"0.55"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.03432","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}