{"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/aligntts-efficient-feed-forward-text-to","title":"AlignTTS: Efficient Feed-Forward Text-to-Speech System without Explicit Alignment","arxiv_id":"2003.01950","date":"2020-03-04","proceeding":null,"authors":["Zhen Zeng","Jianzong Wang","Ning Cheng","Tian Xia","Jing Xiao"],"abstract":"Targeting at both high efficiency and performance, we propose AlignTTS to predict the mel-spectrum in parallel. AlignTTS is based on a Feed-Forward Transformer which generates mel-spectrum from a sequence of characters, and the duration of each character is determined by a duration predictor.Instead of adopting the attention mechanism in Transformer TTS to align text to mel-spectrum, the alignment loss is presented to consider all possible alignments in training by use of dynamic programming. Experiments on the LJSpeech dataset show that our model achieves not only state-of-the-art performance which outperforms Transformer TTS by 0.03 in mean option score (MOS), but also a high efficiency which is more than 50 times faster than real-time.","url_abs":"https://arxiv.org/abs/2003.01950v1","url_pdf":"https://arxiv.org/pdf/2003.01950v1.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":"aligntts-efficient-feed-forward-text-to","repo_url":"https://github.com/coqui-ai/TTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MPL-2.0"}},{"paper_slug":"aligntts-efficient-feed-forward-text-to","repo_url":"https://github.com/mangushev/aligntts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2003.01950","atlas_url":"https://app.syntology.ai/?focus=2003.01950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.01950"}},"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/mangushev/aligntts","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/coqui-ai/TTS","reach":{"status":"ok","spdx":"MPL-2.0"}}],"summary":{"ran_fixture":1,"ran":1,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"listed":{"samples":6,"ran":3,"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":0,"samples":[{"code_sha256_prefix":"873e08c3f15eb1e4","entry":"dropout","repo":"mangushev/aligntts","repo_kind":"listed","path":"model.py","file_url":"https://github.com/mangushev/aligntts/blob/HEAD/model.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"873e08c3f15eb1e4"}},{"code_sha256_prefix":"4d570a07b66b39b3","entry":"make_input_fn","repo":"mangushev/aligntts","repo_kind":"listed","path":"training.py","file_url":"https://github.com/mangushev/aligntts/blob/HEAD/training.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4d570a07b66b39b3"}},{"code_sha256_prefix":"7b84f3e6a96584b4","entry":"reshape_to_matrix","repo":"mangushev/aligntts","repo_kind":"listed","path":"model.py","file_url":"https://github.com/mangushev/aligntts/blob/HEAD/model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7b84f3e6a96584b4"}},{"code_sha256_prefix":"8e282dee546609ce","entry":"audio_example","repo":"mangushev/aligntts","repo_kind":"listed","path":"prepare_data.py","file_url":"https://github.com/mangushev/aligntts/blob/HEAD/prepare_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8e282dee546609ce"}},{"code_sha256_prefix":"50958618b65e514e","entry":"get_assignment_map_from_checkpoint","repo":"mangushev/aligntts","repo_kind":"listed","path":"training.py","file_url":"https://github.com/mangushev/aligntts/blob/HEAD/training.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"50958618b65e514e"}},{"code_sha256_prefix":"3370499aacadb239","entry":"reshape_from_matrix","repo":"mangushev/aligntts","repo_kind":"listed","path":"model.py","file_url":"https://github.com/mangushev/aligntts/blob/HEAD/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3370499aacadb239"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}