{"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/vector-quantized-neural-networks-for-acoustic","title":"Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge","arxiv_id":"2005.09409","date":"2020-05-19","proceeding":null,"authors":["Benjamin van Niekerk","Leanne Nortje","Herman Kamper"],"abstract":"In this paper, we explore vector quantization for acoustic unit discovery. Leveraging unlabelled data, we aim to learn discrete representations of speech that separate phonetic content from speaker-specific details. We propose two neural models to tackle this challenge - both use vector quantization to map continuous features to a finite set of codes. The first model is a type of vector-quantized variational autoencoder (VQ-VAE). The VQ-VAE encodes speech into a sequence of discrete units before reconstructing the audio waveform. Our second model combines vector quantization with contrastive predictive coding (VQ-CPC). The idea is to learn a representation of speech by predicting future acoustic units. We evaluate the models on English and Indonesian data for the ZeroSpeech 2020 challenge. In ABX phone discrimination tests, both models outperform all submissions to the 2019 and 2020 challenges, with a relative improvement of more than 30%. The models also perform competitively on a downstream voice conversion task. Of the two, VQ-CPC performs slightly better in general and is simpler and faster to train. Finally, probing experiments show that vector quantization is an effective bottleneck, forcing the models to discard speaker information.","url_abs":"https://arxiv.org/abs/2005.09409v2","url_pdf":"https://arxiv.org/pdf/2005.09409v2.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":"vector-quantized-neural-networks-for-acoustic","repo_url":"https://github.com/bshall/VectorQuantizedCPC","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"vector-quantized-neural-networks-for-acoustic","repo_url":"https://github.com/bshall/ZeroSpeech","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Acoustic Unit Discovery"},{"task_slug":"voice-conversion","task_name":"Voice Conversion"}],"methods":[{"method_slug":"contrastive-predictive-coding","method_name":"Contrastive Predictive Coding"},{"method_slug":"infonce","method_name":"InfoNCE"},{"method_slug":"vq-vae","method_name":"VQ-VAE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/voice-conversion-on-zerospeech-2019-english","task":"Voice Conversion","dataset":"ZeroSpeech 2019 English","model":"VQ-CPC","rank_in_archive_order":1,"of":2,"metrics":{"Speaker Similarity":"3.8"},"uses_additional_data":true},{"leaderboard":"/sota/voice-conversion-on-zerospeech-2019-english","task":"Voice Conversion","dataset":"ZeroSpeech 2019 English","model":"VQ-VAE","rank_in_archive_order":2,"of":2,"metrics":{"Speaker Similarity":"3.49"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2005.09409","atlas_url":"https://app.syntology.ai/?focus=2005.09409","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":"2005.09409"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2005.09409\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2005.09409"},"call":"get_concepts_for_paper(arxiv_id=\"2005.09409\")"}],"by_repo":[{"repo":"bshall/VectorQuantizedCPC","kind":"named_in_paper","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["1711.00937","1807.03748"],"harvested_for_calls":[{"arxiv_id":"1711.00937","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1711.00937"},"call":"get_harvested_code_for_paper(arxiv_id=\"1711.00937\")"},{"arxiv_id":"1807.03748","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1807.03748"},"call":"get_harvested_code_for_paper(arxiv_id=\"1807.03748\")"}]},{"repo":"bshall/ZeroSpeech","kind":"named_in_paper","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1711.00937"],"harvested_for_calls":[{"arxiv_id":"1711.00937","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1711.00937"},"call":"get_harvested_code_for_paper(arxiv_id=\"1711.00937\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"c87c8810a8e5a1ed8447a239412edf695a2ff9899c8c2985409e1de6e8c66bc6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}