{"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/spectral-normalize-torch","entry":"spectral_normalize_torch","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":2,"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":2,"n_samples_fingerprinted":2,"n_places":8,"n_places_pointer_only":1,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":2},"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":"2504.00858","paper":"/paper/whispering-under-the-eaves-protecting-user","title":"Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systems","date":"2025-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WeifeiJin/AudioShield","path":"mel_processing.py","file_url":"https://github.com/WeifeiJin/AudioShield/blob/HEAD/mel_processing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"26b87488d429896a","mcp_get_code":{"code_sha256":"26b87488d429896a"}},{"arxiv_id":"2412.15322","paper":"/paper/taming-multimodal-joint-training-for-high","title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","date":"2024-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hkchengrex/MMAudio","path":"mmaudio/ext/mel_converter.py","file_url":"https://github.com/hkchengrex/MMAudio/blob/HEAD/mmaudio/ext/mel_converter.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d589f15a67884195","mcp_get_code":{"code_sha256":"d589f15a67884195"}},{"arxiv_id":"2312.01479","paper":"/paper/openvoice-versatile-instant-voice-cloning","title":"OpenVoice: Versatile Instant Voice Cloning","date":"2023-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"myshell-ai/openvoice","path":"openvoice/mel_processing.py","file_url":"https://github.com/myshell-ai/openvoice/blob/HEAD/openvoice/mel_processing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"26b87488d429896a","mcp_get_code":{"code_sha256":"26b87488d429896a"}},{"arxiv_id":"2308.16692","paper":"/paper/speechtokenizer-unified-speech-tokenizer-for","title":"SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models","date":"2023-08-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhangXInFD/SpeechTokenizer","path":"speechtokenizer/trainer/loss.py","file_url":"https://github.com/ZhangXInFD/SpeechTokenizer/blob/HEAD/speechtokenizer/trainer/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bcadb9daef59d785","mcp_get_code":{"code_sha256":"bcadb9daef59d785"}},{"arxiv_id":"2305.19709","paper":"/paper/xphonebert-a-pre-trained-multilingual-model","title":"XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech","date":"2023-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vinairesearch/xphonebert","path":"VITS_with_XPhoneBERT/mel_processing.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/mel_processing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"26b87488d429896a","mcp_get_code":{"code_sha256":"26b87488d429896a"}},{"arxiv_id":"2206.04658","paper":"/paper/bigvgan-a-universal-neural-vocoder-with-large","title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","date":"2022-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sh-lee-prml/BigVGAN","path":"mel_processing.py","file_url":"https://github.com/sh-lee-prml/BigVGAN/blob/HEAD/mel_processing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"26b87488d429896a","mcp_get_code":{"code_sha256":"26b87488d429896a"}},{"arxiv_id":"2110.02500","paper":"/paper/mediumvc-any-to-any-voice-conversion-using","title":"MediumVC: Any-to-any voice conversion using synthetic specific-speaker speeches as intermedium features","date":"2021-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brightgu/mediumvc","path":"Any2Any/pre_feature/figure_spkemb_mel.py","file_url":"https://github.com/brightgu/mediumvc/blob/HEAD/Any2Any/pre_feature/figure_spkemb_mel.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f3b4807194412f70","mcp_get_code":{"code_sha256":"f3b4807194412f70"}},{"arxiv_id":"2106.06103","paper":"/paper/conditional-variational-autoencoder-with","title":"Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech","date":null,"month_inferred_from_arxiv_id":"2021-06","title_source":"archive","repo":"jaywalnut310/vits","path":"mel_processing.py","file_url":"https://github.com/jaywalnut310/vits/blob/HEAD/mel_processing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"26b87488d429896a","mcp_get_code":{"code_sha256":"26b87488d429896a"}}]}