{"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/from-discrete-tokens-to-high-fidelity-audio","title":"From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion","arxiv_id":"2308.02560","date":"2023-08-02","proceeding":"NeurIPS 2023 11","authors":[],"abstract":"Deep generative models can generate high-fidelity audio conditioned on various types of representations (e.g., mel-spectrograms, Mel-frequency Cepstral Coefficients (MFCC)). Recently, such models have been used to synthesize audio waveforms conditioned on highly compressed representations. Although such methods produce impressive results, they are prone to generate audible artifacts when the conditioning is flawed or imperfect. An alternative modeling approach is to use diffusion models. However, these have mainly been used as speech vocoders (i.e., conditioned on mel-spectrograms) or generating relatively low sampling rate signals. In this work, we propose a high-fidelity multi-band diffusion-based framework that generates any type of audio modality (e.g., speech, music, environmental sounds) from low-bitrate discrete representations. At equal bit rate, the proposed approach outperforms state-of-the-art generative techniques in terms of perceptual quality. Training and, evaluation code, along with audio samples, are available on the facebookresearch/audiocraft Github page.","url_abs":"https://arxiv.org/abs/2308.02560v2","url_pdf":"https://arxiv.org/pdf/2308.02560v2.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":"from-discrete-tokens-to-high-fidelity-audio","repo_url":"https://github.com/metavoiceio/metavoice-src","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2308.02560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.02560"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/metavoiceio/metavoice-src","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"unverified":10},"by_repo_kind":{"listed":{"samples":11,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"5b6f45360aa68edd","entry":"multinomial_sample_one_no_sync","repo":"metavoiceio/metavoice-src","repo_kind":"listed","path":"fam/llm/fast_inference_utils.py","file_url":"https://github.com/metavoiceio/metavoice-src/blob/HEAD/fam/llm/fast_inference_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5b6f45360aa68edd"}},{"code_sha256_prefix":"55ec8fea60e1d7e7","entry":"dynamically_quantize_per_channel","repo":"metavoiceio/metavoice-src","repo_kind":"listed","path":"fam/llm/fast_quantize.py","file_url":"https://github.com/metavoiceio/metavoice-src/blob/HEAD/fam/llm/fast_quantize.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"55ec8fea60e1d7e7"}},{"code_sha256_prefix":"5b392490c1dd0292","entry":"find_multiple","repo":"metavoiceio/metavoice-src","repo_kind":"listed","path":"fam/llm/fast_model.py","file_url":"https://github.com/metavoiceio/metavoice-src/blob/HEAD/fam/llm/fast_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5b392490c1dd0292"}},{"code_sha256_prefix":"000187477d99d590","entry":"get_cached_embedding","repo":"metavoiceio/metavoice-src","repo_kind":"listed","path":"fam/llm/inference.py","file_url":"https://github.com/metavoiceio/metavoice-src/blob/HEAD/fam/llm/inference.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"000187477d99d590"}},{"code_sha256_prefix":"cf90023e439d59c2","entry":"get_cached_file","repo":"metavoiceio/metavoice-src","repo_kind":"listed","path":"fam/llm/inference.py","file_url":"https://github.com/metavoiceio/metavoice-src/blob/HEAD/fam/llm/inference.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cf90023e439d59c2"}},{"code_sha256_prefix":"dbabfb89a4b530ac","entry":"get_group_qparams","repo":"metavoiceio/metavoice-src","repo_kind":"listed","path":"fam/llm/fast_quantize.py","file_url":"https://github.com/metavoiceio/metavoice-src/blob/HEAD/fam/llm/fast_quantize.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dbabfb89a4b530ac"}},{"code_sha256_prefix":"9ff14bb645be7875","entry":"logits_to_probs","repo":"metavoiceio/metavoice-src","repo_kind":"listed","path":"fam/llm/fast_inference_utils.py","file_url":"https://github.com/metavoiceio/metavoice-src/blob/HEAD/fam/llm/fast_inference_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9ff14bb645be7875"}},{"code_sha256_prefix":"74026bf479b959d4","entry":"make_output_file_path","repo":"metavoiceio/metavoice-src","repo_kind":"listed","path":"fam/llm/enhancers.py","file_url":"https://github.com/metavoiceio/metavoice-src/blob/HEAD/fam/llm/enhancers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"74026bf479b959d4"}},{"code_sha256_prefix":"146cdcef0c195fd7","entry":"pack_scales_and_zeros","repo":"metavoiceio/metavoice-src","repo_kind":"listed","path":"fam/llm/fast_quantize.py","file_url":"https://github.com/metavoiceio/metavoice-src/blob/HEAD/fam/llm/fast_quantize.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"146cdcef0c195fd7"}},{"code_sha256_prefix":"4f354d0b20a057d8","entry":"strip_prefix","repo":"metavoiceio/metavoice-src","repo_kind":"listed","path":"fam/llm/finetune.py","file_url":"https://github.com/metavoiceio/metavoice-src/blob/HEAD/fam/llm/finetune.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4f354d0b20a057d8"}},{"code_sha256_prefix":"b18c8665684fec61","entry":"top_p_sample","repo":"metavoiceio/metavoice-src","repo_kind":"listed","path":"fam/llm/fast_inference_utils.py","file_url":"https://github.com/metavoiceio/metavoice-src/blob/HEAD/fam/llm/fast_inference_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b18c8665684fec61"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}