{"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/griffin-lim","entry":"griffin_lim","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":16,"n_papers_ran":15,"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":3,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":17,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":0,"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":"2406.04350","paper":"/paper/prompt-guided-precise-audio-editing-with","title":"Prompt-guided Precise Audio Editing with Diffusion Models","date":"2024-05-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haoheliu/audioldm","path":"audioldm/audio/audio_processing.py","file_url":"https://github.com/haoheliu/audioldm/blob/HEAD/audioldm/audio/audio_processing.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":"9f9ec26d4cdfdf7d","mcp_get_code":{"code_sha256":"9f9ec26d4cdfdf7d"}},{"arxiv_id":"2404.18398","paper":"/paper/mm-tts-a-unified-framework-for-multimodal","title":"UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts","date":"2024-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kttrcdl/umetts","path":"EMITTS/Tacotron2/audio_processing.py","file_url":"https://github.com/kttrcdl/umetts/blob/HEAD/EMITTS/Tacotron2/audio_processing.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"code_sha256_prefix":"9f9ec26d4cdfdf7d","mcp_get_code":{"code_sha256":"9f9ec26d4cdfdf7d"}},{"arxiv_id":"2301.12503","paper":"/paper/audioldm-text-to-audio-generation-with-latent","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","date":"2023-01-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haoheliu/audioldm_eval","path":"audioldm_eval/audio/audio_processing.py","file_url":"https://github.com/haoheliu/audioldm_eval/blob/HEAD/audioldm_eval/audio/audio_processing.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9f9ec26d4cdfdf7d","mcp_get_code":{"code_sha256":"9f9ec26d4cdfdf7d"}},{"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":"NVIDIA/tacotron2","path":"audio_processing.py","file_url":"https://github.com/NVIDIA/tacotron2/blob/HEAD/audio_processing.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"9f9ec26d4cdfdf7d","mcp_get_code":{"code_sha256":"9f9ec26d4cdfdf7d"}},{"arxiv_id":"2105.06337","paper":"/paper/grad-tts-a-diffusion-probabilistic-model-for","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","date":"2021-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WelkinYang/GradTTS","path":"audio_processing.py","file_url":"https://github.com/WelkinYang/GradTTS/blob/HEAD/audio_processing.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9f9ec26d4cdfdf7d","mcp_get_code":{"code_sha256":"9f9ec26d4cdfdf7d"}},{"arxiv_id":"2005.11129","paper":"/paper/glow-tts-a-generative-flow-for-text-to-speech","title":"Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search","date":"2020-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ankurdhuriya/multispeaker-glow-tts","path":"audio_processing.py","file_url":"https://github.com/ankurdhuriya/multispeaker-glow-tts/blob/HEAD/audio_processing.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9f9ec26d4cdfdf7d","mcp_get_code":{"code_sha256":"9f9ec26d4cdfdf7d"}},{"arxiv_id":"2005.05957","paper":"/paper/flowtron-an-autoregressive-flow-based","title":"Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis","date":"2020-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVIDIA/flowtron","path":"audio_processing.py","file_url":"https://github.com/NVIDIA/flowtron/blob/HEAD/audio_processing.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9f9ec26d4cdfdf7d","mcp_get_code":{"code_sha256":"9f9ec26d4cdfdf7d"}},{"arxiv_id":"2005.05106","paper":"/paper/multi-band-melgan-faster-waveform-generation","title":"Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speech","date":null,"month_inferred_from_arxiv_id":"2020-05","title_source":"archive","repo":"rishikksh20/melgan","path":"utils/audio_processing.py","file_url":"https://github.com/rishikksh20/melgan/blob/HEAD/utils/audio_processing.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"9f9ec26d4cdfdf7d","mcp_get_code":{"code_sha256":"9f9ec26d4cdfdf7d"}},{"arxiv_id":"1912.01219","paper":"/paper/waveflow-a-compact-flow-based-model-for-raw-1","title":"WaveFlow: A Compact Flow-based Model for Raw Audio","date":"2019-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"L0SG/WaveFlow","path":"tacotron2_custom/audio_processing.py","file_url":"https://github.com/L0SG/WaveFlow/blob/HEAD/tacotron2_custom/audio_processing.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"9f9ec26d4cdfdf7d","mcp_get_code":{"code_sha256":"9f9ec26d4cdfdf7d"}},{"arxiv_id":"1910.06711","paper":"/paper/melgan-generative-adversarial-networks-for","title":"MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis","date":"2019-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seungwonpark/melgan","path":"utils/audio_processing.py","file_url":"https://github.com/seungwonpark/melgan/blob/HEAD/utils/audio_processing.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"9f9ec26d4cdfdf7d","mcp_get_code":{"code_sha256":"9f9ec26d4cdfdf7d"}},{"arxiv_id":"1909.11646","paper":"/paper/high-fidelity-speech-synthesis-with-1","title":"High Fidelity Speech Synthesis with Adversarial Networks","date":"2019-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"izzajalandoni/tts_models","path":"audio_processing.py","file_url":"https://github.com/izzajalandoni/tts_models/blob/HEAD/audio_processing.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"code_sha256_prefix":"9f9ec26d4cdfdf7d","mcp_get_code":{"code_sha256":"9f9ec26d4cdfdf7d"}},{"arxiv_id":"1907.04448","paper":"/paper/learning-to-speak-fluently-in-a-foreign","title":"Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning","date":"2019-07-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Jeevesh8/Cross-Lingual-Voice-Cloning","path":"audio_processing.py","file_url":"https://github.com/Jeevesh8/Cross-Lingual-Voice-Cloning/blob/HEAD/audio_processing.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"code_sha256_prefix":"9f9ec26d4cdfdf7d","mcp_get_code":{"code_sha256":"9f9ec26d4cdfdf7d"}},{"arxiv_id":"1812.04342","paper":"/paper/learning-latent-representations-for-style","title":"Learning latent representations for style control and transfer in end-to-end speech synthesis","date":"2018-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jinhan/tacotron2-vae","path":"audio_processing.py","file_url":"https://github.com/jinhan/tacotron2-vae/blob/HEAD/audio_processing.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"code_sha256_prefix":"9f9ec26d4cdfdf7d","mcp_get_code":{"code_sha256":"9f9ec26d4cdfdf7d"}},{"arxiv_id":"1811.02122","paper":"/paper/robust-and-fine-grained-prosody-control-of","title":"Robust and fine-grained prosody control of end-to-end speech synthesis","date":"2018-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"keonlee9420/Robust_Fine_Grained_Prosody_Control","path":"audio_processing.py","file_url":"https://github.com/keonlee9420/Robust_Fine_Grained_Prosody_Control/blob/HEAD/audio_processing.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"code_sha256_prefix":"9f9ec26d4cdfdf7d","mcp_get_code":{"code_sha256":"9f9ec26d4cdfdf7d"}},{"arxiv_id":"1803.09017","paper":"/paper/style-tokens-unsupervised-style-modeling","title":"Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis","date":"2018-03-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jinhan/tacotron2-gst","path":"audio_processing.py","file_url":"https://github.com/jinhan/tacotron2-gst/blob/HEAD/audio_processing.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"code_sha256_prefix":"9f9ec26d4cdfdf7d","mcp_get_code":{"code_sha256":"9f9ec26d4cdfdf7d"}},{"arxiv_id":"1803.09017","paper":"/paper/style-tokens-unsupervised-style-modeling","title":"Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis","date":"2018-03-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"foamliu/GST-Tacotron-v2","path":"audio_processing.py","file_url":"https://github.com/foamliu/GST-Tacotron-v2/blob/HEAD/audio_processing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e274cfa39f3d6bf9","mcp_get_code":{"code_sha256":"e274cfa39f3d6bf9"}},{"arxiv_id":"1607.05666","paper":"/paper/trainable-frontend-for-robust-and-far-field","title":"Trainable Frontend For Robust and Far-Field Keyword Spotting","date":"2016-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"asteroid-team/asteroid-filterbanks","path":"asteroid_filterbanks/griffin_lim.py","file_url":"https://github.com/asteroid-team/asteroid-filterbanks/blob/HEAD/asteroid_filterbanks/griffin_lim.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8923f688906e1436","mcp_get_code":{"code_sha256":"8923f688906e1436"}}]}