{"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/stft-magnitude","entry":"stft_magnitude","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":8,"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":4,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":0,"unverified":3},"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":"2505.19328","paper":"/paper/bah-dataset-for-ambivalence-hesitancy","title":"BAH Dataset for Ambivalence/Hesitancy Recognition in Videos for Behavioural Change","date":"2025-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"harritaylor/torchvggish","path":"torchvggish/mel_features.py","file_url":"https://github.com/harritaylor/torchvggish/blob/HEAD/torchvggish/mel_features.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"bcec5b9bde143277","mcp_get_code":{"code_sha256":"bcec5b9bde143277"}},{"arxiv_id":"2402.16321","paper":"/paper/self-supervised-speech-quality-estimation-and","title":"Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speech","date":"2024-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JasonSWFu/VQscore","path":"inference.py","file_url":"https://github.com/JasonSWFu/VQscore/blob/HEAD/inference.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c05fc59409ba925c","mcp_get_code":{"code_sha256":"c05fc59409ba925c"}},{"arxiv_id":"2210.12300","paper":"/paper/beans-the-benchmark-of-animal-sounds","title":"BEANS: The Benchmark of Animal Sounds","date":null,"month_inferred_from_arxiv_id":"2022-10","title_source":"archive","repo":"earthspecies/beans","path":"beans/torchvggish/mel_features.py","file_url":"https://github.com/earthspecies/beans/blob/HEAD/beans/torchvggish/mel_features.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fcb574ecc2b946ef","mcp_get_code":{"code_sha256":"fcb574ecc2b946ef"}},{"arxiv_id":"2110.08791","paper":"/paper/taming-visually-guided-sound-generation","title":"Taming Visually Guided Sound Generation","date":"2021-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"v-iashin/video_features","path":"models/vggish/vggish_src/mel_features.py","file_url":"https://github.com/v-iashin/video_features/blob/HEAD/models/vggish/vggish_src/mel_features.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bcec5b9bde143277","mcp_get_code":{"code_sha256":"bcec5b9bde143277"}},{"arxiv_id":"1909.06654","paper":"/paper/musicnn-pre-trained-convolutional-neural","title":"musicnn: Pre-trained convolutional neural networks for music audio tagging","date":"2019-09-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jordipons/sklearn-audio-transfer-learning","path":"src/mel_features.py","file_url":"https://github.com/jordipons/sklearn-audio-transfer-learning/blob/HEAD/src/mel_features.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"ISC","inline_ok":true,"code_sha256_prefix":"bcec5b9bde143277","mcp_get_code":{"code_sha256":"bcec5b9bde143277"}},{"arxiv_id":"1903.00765","paper":"/paper/weakly-labelled-audioset-tagging-with-1","title":"Weakly Labelled AudioSet Tagging with Attention Neural Networks","date":null,"month_inferred_from_arxiv_id":"2019-03","title_source":"archive","repo":"qiuqiangkong/audioset_classification","path":"extract_audioset_embedding/mel_features.py","file_url":"https://github.com/qiuqiangkong/audioset_classification/blob/HEAD/extract_audioset_embedding/mel_features.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"bcec5b9bde143277","mcp_get_code":{"code_sha256":"bcec5b9bde143277"}},{"arxiv_id":"1803.02353","paper":"/paper/multi-level-attention-model-for-weakly","title":"Multi-level Attention Model for Weakly Supervised Audio Classification","date":"2018-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IBM/MAX-Audio-Classifier","path":"core/mel_features.py","file_url":"https://github.com/IBM/MAX-Audio-Classifier/blob/HEAD/core/mel_features.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":"0f0fa853ceaa04db","mcp_get_code":{"code_sha256":"0f0fa853ceaa04db"}},{"arxiv_id":"1609.09430","paper":"/paper/cnn-architectures-for-large-scale-audio","title":"CNN Architectures for Large-Scale Audio Classification","date":"2016-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IBM/MAX-Audio-Embedding-Generator","path":"core/mel_features.py","file_url":"https://github.com/IBM/MAX-Audio-Embedding-Generator/blob/HEAD/core/mel_features.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":"0f0fa853ceaa04db","mcp_get_code":{"code_sha256":"0f0fa853ceaa04db"}}]}