{"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/load-audio","entry":"load_audio","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":10,"n_papers_ran":1,"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":8,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":10,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":7},"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":"2609.13445","paper":"/paper/arxiv-2609-13445","title":"CAUSAL ANALYSIS AND MITIGATION OF SPURIOUS ONSETS IN FULL-DUPLEX SPEECH LLMS","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"KentoNishi/icassp27-spurious-onsets","path":"protocol.py","file_url":"https://github.com/KentoNishi/icassp27-spurious-onsets/blob/HEAD/protocol.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5d380dffd36320b0","mcp_get_code":{"code_sha256":"5d380dffd36320b0"}},{"arxiv_id":"2606.04205","paper":"/paper/arxiv-2606-04205","title":"DetectZoo: A Unified Toolkit for AI-Generated Content Detection Across Text, Audio, and Image Modalities","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"sadjadeb/DetectZoo","path":"detectzoo/utils/io.py","file_url":"https://github.com/sadjadeb/DetectZoo/blob/HEAD/detectzoo/utils/io.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5634834f5c8fd817","mcp_get_code":{"code_sha256":"5634834f5c8fd817"}},{"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":"80abc0b281d75575","mcp_get_code":{"code_sha256":"80abc0b281d75575"}},{"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":"80abc0b281d75575","mcp_get_code":{"code_sha256":"80abc0b281d75575"}},{"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":"1e0fb79d41422266","mcp_get_code":{"code_sha256":"1e0fb79d41422266"}},{"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":"80abc0b281d75575","mcp_get_code":{"code_sha256":"80abc0b281d75575"}},{"arxiv_id":"2309.14405","paper":"/paper/joint-audio-and-speech-understanding","title":"Joint Audio and Speech Understanding","date":"2023-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YuanGongND/ltu","path":"src/ltu_as/inference_batch.py","file_url":"https://github.com/YuanGongND/ltu/blob/HEAD/src/ltu_as/inference_batch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b5c3b0851878b618","mcp_get_code":{"code_sha256":"b5c3b0851878b618"}},{"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/utils_data.py","file_url":"https://github.com/YasserdahouML/Lip2Vec/blob/HEAD/datasets/utils_data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b3510aa8b8ed8518","mcp_get_code":{"code_sha256":"b3510aa8b8ed8518"}},{"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":"collabora/whisperlive","path":"whisper_live/diarization.py","file_url":"https://github.com/collabora/whisperlive/blob/HEAD/whisper_live/diarization.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"34dd5baae0e5830e","mcp_get_code":{"code_sha256":"34dd5baae0e5830e"}},{"arxiv_id":"2008.02734","paper":"/paper/exact-parallelizable-dynamic-time-warping","title":"Exact, Parallelizable Dynamic Time Warping Alignment with Linear Memory","date":"2020-08-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ctralie/linmdtw","path":"linmdtw/audiotools.py","file_url":"https://github.com/ctralie/linmdtw/blob/HEAD/linmdtw/audiotools.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":"5f0af94e039bd318","mcp_get_code":{"code_sha256":"5f0af94e039bd318"}}]}