{"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/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":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}