{"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":"/paper/end-to-end-adversarial-text-to-speech","title":"End-to-End Adversarial Text-to-Speech","arxiv_id":"2006.03575","date":"2020-06-05","proceeding":"ICLR 2021 1","authors":["Jeff Donahue","Sander Dieleman","Mikołaj Bińkowski","Erich Elsen","Karen Simonyan"],"abstract":"Modern text-to-speech synthesis pipelines typically involve multiple processing stages, each of which is designed or learnt independently from the rest. In this work, we take on the challenging task of learning to synthesise speech from normalised text or phonemes in an end-to-end manner, resulting in models which operate directly on character or phoneme input sequences and produce raw speech audio outputs. Our proposed generator is feed-forward and thus efficient for both training and inference, using a differentiable alignment scheme based on token length prediction. It learns to produce high fidelity audio through a combination of adversarial feedback and prediction losses constraining the generated audio to roughly match the ground truth in terms of its total duration and mel-spectrogram. To allow the model to capture temporal variation in the generated audio, we employ soft dynamic time warping in the spectrogram-based prediction loss. The resulting model achieves a mean opinion score exceeding 4 on a 5 point scale, which is comparable to the state-of-the-art models relying on multi-stage training and additional supervision.","url_abs":"https://arxiv.org/abs/2006.03575v3","url_pdf":"https://arxiv.org/pdf/2006.03575v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"end-to-end-adversarial-text-to-speech","repo_url":"https://github.com/keonlee9420/WaveGrad2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"end-to-end-adversarial-text-to-speech","repo_url":"https://github.com/yanggeng1995/EATS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-text","task_name":"Adversarial Text"},{"task_slug":"dynamic-time-warping","task_name":"Dynamic Time Warping"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-synthesis","task_name":"Text-To-Speech Synthesis"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.03575","atlas_url":"https://app.syntology.ai/?focus=2006.03575","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.03575"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yanggeng1995/EATS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/keonlee9420/WaveGrad2","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":10,"unverified":2},"by_repo_kind":{"listed":{"samples":12,"ran":10,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":12,"samples":[{"code_sha256_prefix":"8a3de745cf9b3033","entry":"Aligner","repo":"yanggeng1995/EATS","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/yanggeng1995/EATS/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8a3de745cf9b3033"}},{"code_sha256_prefix":"48d275866de6c91e","entry":"BatchNorm1dLayer","repo":"yanggeng1995/EATS","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/yanggeng1995/EATS/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"48d275866de6c91e"}},{"code_sha256_prefix":"22bd8db4b8e3b7e1","entry":"ConditionalBatchNorm1d","repo":"yanggeng1995/EATS","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/yanggeng1995/EATS/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"22bd8db4b8e3b7e1"}},{"code_sha256_prefix":"2c4b25e8c21134ff","entry":"Conv1d","repo":"yanggeng1995/EATS","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/yanggeng1995/EATS/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2c4b25e8c21134ff"}},{"code_sha256_prefix":"bb61ffc1f9389bac","entry":"DilatedConvBlock","repo":"yanggeng1995/EATS","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/yanggeng1995/EATS/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bb61ffc1f9389bac"}},{"code_sha256_prefix":"aa6b42abfec110ef","entry":"Encoder","repo":"yanggeng1995/EATS","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/yanggeng1995/EATS/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aa6b42abfec110ef"}},{"code_sha256_prefix":"a30a77bbb2877a18","entry":"ExpandFrame","repo":"yanggeng1995/EATS","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/yanggeng1995/EATS/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a30a77bbb2877a18"}},{"code_sha256_prefix":"013522fc606d3e1c","entry":"GBlock","repo":"yanggeng1995/EATS","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/yanggeng1995/EATS/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"013522fc606d3e1c"}},{"code_sha256_prefix":"357894f4132b8a28","entry":"Linear","repo":"yanggeng1995/EATS","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/yanggeng1995/EATS/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"357894f4132b8a28"}},{"code_sha256_prefix":"73d986b76e559e28","entry":"UpsampleNet","repo":"yanggeng1995/EATS","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/yanggeng1995/EATS/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"73d986b76e559e28"}},{"code_sha256_prefix":"e3eff62b8d4c6ebf","entry":"Decoder","repo":"yanggeng1995/EATS","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/yanggeng1995/EATS/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e3eff62b8d4c6ebf"}},{"code_sha256_prefix":"312415717975e25e","entry":"EETS","repo":"yanggeng1995/EATS","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/yanggeng1995/EATS/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"312415717975e25e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}