{"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":"/code/mel-filters","entry":"mel_filters","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":9,"n_papers_ran":0,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":4,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":9,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":4},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2604.13073","paper":"/paper/arxiv-2604-13073","title":"OmniTrace: A Unified Framework for Generation-Time Attribution in Omni-Modal LLMs","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"openai/whisper","path":"whisper/audio.py","file_url":"https://github.com/openai/whisper/blob/HEAD/whisper/audio.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"12c6c409a1e359c3","mcp_get_code":{"code_sha256":"12c6c409a1e359c3"}},{"arxiv_id":"2510.26096","paper":"/paper/arxiv-2510-26096","title":"ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio-Language Models","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"WeifeiJin/ALMGuard","path":"whisper/audio.py","file_url":"https://github.com/WeifeiJin/ALMGuard/blob/HEAD/whisper/audio.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"12c6c409a1e359c3","mcp_get_code":{"code_sha256":"12c6c409a1e359c3"}},{"arxiv_id":"2506.08967","paper":"/paper/2506-08967","title":"Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model","date":"2025-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stepfun-ai/step-audio","path":"funasr_detach/models/whisper/utils/audio.py","file_url":"https://github.com/stepfun-ai/step-audio/blob/HEAD/funasr_detach/models/whisper/utils/audio.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"edf924293b4b2375","mcp_get_code":{"code_sha256":"edf924293b4b2375"}},{"arxiv_id":"2409.08881","paper":"/paper/data-efficient-child-adult-speaker","title":"Data Efficient Child-Adult Speaker Diarization with Simulated Conversations","date":"2024-09-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"usc-sail/child-adult-diarization","path":"whisper-modeling/models/whisper.py","file_url":"https://github.com/usc-sail/child-adult-diarization/blob/HEAD/whisper-modeling/models/whisper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fac6d3517cd4d773","mcp_get_code":{"code_sha256":"fac6d3517cd4d773"}},{"arxiv_id":"2406.10082","paper":"/paper/whisper-flamingo-integrating-visual-features","title":"Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation","date":"2024-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"roudimit/whisper-flamingo","path":"whisper/audio.py","file_url":"https://github.com/roudimit/whisper-flamingo/blob/HEAD/whisper/audio.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"12c6c409a1e359c3","mcp_get_code":{"code_sha256":"12c6c409a1e359c3"}},{"arxiv_id":"2406.08800","paper":"/paper/can-synthetic-audio-from-generative","title":"Can Synthetic Audio From Generative Foundation Models Assist Audio Recognition and Speech Modeling?","date":"2024-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"usc-sail/synthaudio","path":"src/models/whisper.py","file_url":"https://github.com/usc-sail/synthaudio/blob/HEAD/src/models/whisper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fac6d3517cd4d773","mcp_get_code":{"code_sha256":"fac6d3517cd4d773"}},{"arxiv_id":"2308.06112","paper":"/paper/lip2vec-efficient-and-robust-visual-speech","title":"Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping","date":"2023-08-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YasserdahouML/Lip2Vec","path":"datasets/audio.py","file_url":"https://github.com/YasserdahouML/Lip2Vec/blob/HEAD/datasets/audio.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"edf924293b4b2375","mcp_get_code":{"code_sha256":"edf924293b4b2375"}},{"arxiv_id":"2306.01428","paper":"/paper/improved-deepfake-detection-using-whisper","title":"Improved DeepFake Detection Using Whisper Features","date":"2023-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"piotrkawa/deepfake-whisper-features","path":"src/models/whisper_main.py","file_url":"https://github.com/piotrkawa/deepfake-whisper-features/blob/HEAD/src/models/whisper_main.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"287787d54e6c2146","mcp_get_code":{"code_sha256":"287787d54e6c2146"}},{"arxiv_id":"2212.04356","paper":"/paper/robust-speech-recognition-via-large-scale-1","title":"Robust Speech Recognition via Large-Scale Weak Supervision","date":"2022-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"briansidp/whisperbiasing","path":"whisper/audio.py","file_url":"https://github.com/briansidp/whisperbiasing/blob/HEAD/whisper/audio.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"edf924293b4b2375","mcp_get_code":{"code_sha256":"edf924293b4b2375"}}]}