{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"syntology_url":"https://syntology.ai/paper/2205.03432","atlas_url":"https://app.syntology.ai/?focus=2205.03432","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2205.03432"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2205.03432\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2205.03432"},"call":"get_concepts_for_paper(arxiv_id=\"2205.03432\")"}],"by_repo":[{"repo":"YuanGongND/gopt","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"a92eb1156097846bde5faf720a49369e95088a75c037b5329cc95c2182c294b9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}