{"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/multi-cmgan-leveraging-multi-objective-speech","title":"Multi-CMGAN+/+: Leveraging Multi-Objective Speech Quality Metric Prediction for Speech Enhancement","arxiv_id":"2312.08979","date":"2023-12-14","proceeding":null,"authors":["George Close","William Ravenscroft","Thomas Hain","Stefan Goetze"],"abstract":"Neural network based approaches to speech enhancement have shown to be particularly powerful, being able to leverage a data-driven approach to result in a significant performance gain versus other approaches. Such approaches are reliant on artificially created labelled training data such that the neural model can be trained using intrusive loss functions which compare the output of the model with clean reference speech. Performance of such systems when enhancing real-world audio often suffers relative to their performance on simulated test data. In this work, a non-intrusive multi-metric prediction approach is introduced, wherein a model trained on artificial labelled data using inference of an adversarially trained metric prediction neural network. The proposed approach shows improved performance versus state-of-the-art systems on the recent CHiME-7 challenge \\ac{UDASE} task evaluation sets.","url_abs":"https://arxiv.org/abs/2312.08979v1","url_pdf":"https://arxiv.org/pdf/2312.08979v1.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"multi-cmgan-leveraging-multi-objective-speech","repo_url":"https://github.com/leto19/multimetricganplusplus","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.08979","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08979"}},"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/leto19/multimetricganplusplus","reach":{"status":"ok"}}],"summary":{"ran_violates":3,"ran":2},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":5,"samples":[{"code_sha256_prefix":"a41cb31b42e919b1","entry":"calc_same_padding","repo":"leto19/multimetricganplusplus","repo_kind":"official","path":"models/CMGAN/conformer.py","file_url":"https://github.com/leto19/multimetricganplusplus/blob/HEAD/models/CMGAN/conformer.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a41cb31b42e919b1"}},{"code_sha256_prefix":"59bcee2a1aec4892","entry":"compute_sisdr","repo":"leto19/multimetricganplusplus","repo_kind":"official","path":"metrics/sisdr_metric.py","file_url":"https://github.com/leto19/multimetricganplusplus/blob/HEAD/metrics/sisdr_metric.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"59bcee2a1aec4892"}},{"code_sha256_prefix":"60fff7c3c400d7ff","entry":"default","repo":"leto19/multimetricganplusplus","repo_kind":"official","path":"models/CMGAN/conformer.py","file_url":"https://github.com/leto19/multimetricganplusplus/blob/HEAD/models/CMGAN/conformer.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"60fff7c3c400d7ff"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"leto19/multimetricganplusplus","repo_kind":"official","path":"models/CMGAN/conformer.py","file_url":"https://github.com/leto19/multimetricganplusplus/blob/HEAD/models/CMGAN/conformer.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"797e145aec670fd6","entry":"xavier_init_layer","repo":"leto19/multimetricganplusplus","repo_kind":"official","path":"models/degen.py","file_url":"https://github.com/leto19/multimetricganplusplus/blob/HEAD/models/degen.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"797e145aec670fd6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}