{"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/improving-opus-low-bit-rate-quality-with","title":"Improving Opus Low Bit Rate Quality with Neural Speech Synthesis","arxiv_id":"1905.04628","date":"2020-08-10","proceeding":null,"authors":[],"abstract":"The voice mode of the Opus audio coder can compress wideband speech at bit\nrates ranging from 6 kb/s to 40 kb/s. However, Opus is at its core a waveform\nmatching coder, and as the rate drops below 10 kb/s, quality degrades quickly.\nAs the rate reduces even further, parametric coders tend to perform better than\nwaveform coders. In this paper we propose a backward-compatible way of\nimproving low bit rate Opus quality by re-synthesizing speech from the decoded\nparameters. We compare two different neural generative models, WaveNet and\nLPCNet. WaveNet is a powerful, high-complexity, and high-latency architecture\nthat is not feasible for a practical system, yet provides a best known\nachievable quality with generative models. LPCNet is a low-complexity,\nlow-latency RNN-based generative model, and practically implementable on mobile\nphones. We apply these systems with parameters from Opus coded at 6 kb/s as\nconditioning features for the generative models. A listening test shows that\nfor the same 6 kb/s Opus bit stream, synthesized speech using LPCNet clearly\noutperforms the output of the standard Opus decoder. This opens up ways to\nimprove the decoding quality of existing speech and audio waveform coders\nwithout breaking compatibility.","url_abs":"http://arxiv.org/abs/1905.04628v3","url_pdf":"http://arxiv.org/pdf/1905.04628v3.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":"improving-opus-low-bit-rate-quality-with","repo_url":"https://github.com/mozilla/LPCNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"mozilla/LPCNet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1903.12087"],"harvested_for_calls":[{"arxiv_id":"1903.12087","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1903.12087"},"call":"get_harvested_code_for_paper(arxiv_id=\"1903.12087\")"}]}],"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":"42cc6dae7b1f037656a962d10f6b6adf12acbc6fd516d1b494c7ec8540812144","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}