{"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/non-attentive-tacotron-robust-and-1","title":"Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling","arxiv_id":"2010.04301","date":"2020-10-08","proceeding":null,"authors":["Jonathan Shen","Ye Jia","Mike Chrzanowski","Yu Zhang","Isaac Elias","Heiga Zen","Yonghui Wu"],"abstract":"This paper presents Non-Attentive Tacotron based on the Tacotron 2 text-to-speech model, replacing the attention mechanism with an explicit duration predictor. This improves robustness significantly as measured by unaligned duration ratio and word deletion rate, two metrics introduced in this paper for large-scale robustness evaluation using a pre-trained speech recognition model. With the use of Gaussian upsampling, Non-Attentive Tacotron achieves a 5-scale mean opinion score for naturalness of 4.41, slightly outperforming Tacotron 2. The duration predictor enables both utterance-wide and per-phoneme control of duration at inference time. When accurate target durations are scarce or unavailable in the training data, we propose a method using a fine-grained variational auto-encoder to train the duration predictor in a semi-supervised or unsupervised manner, with results almost as good as supervised training.","url_abs":"https://arxiv.org/abs/2010.04301v4","url_pdf":"https://arxiv.org/pdf/2010.04301v4.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":"non-attentive-tacotron-robust-and-1","repo_url":"https://github.com/Garvit-32/Non-Attentive-Tacotron","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"non-attentive-tacotron-robust-and-1","repo_url":"https://github.com/IMDxD/NonAttentiveTacotron","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"non-attentive-tacotron-robust-and-1","repo_url":"https://github.com/JoungheeKim/Non-Attentive-Tacotron","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"non-attentive-tacotron-robust-and-1","repo_url":"https://github.com/balan/text-to-speech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"non-attentive-tacotron-robust-and-1","repo_url":"https://github.com/maum-ai/wavegrad2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"non-attentive-tacotron-robust-and-1","repo_url":"https://github.com/mindslab-ai/wavegrad2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bigru","method_name":"BiGRU"},{"method_slug":"bilstm","method_name":"BiLSTM"},{"method_slug":"cbhg","method_name":"CBHG"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dilated-causal-convolution","method_name":"Dilated Causal Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gru","method_name":"GRU"},{"method_slug":"griffin-lim-algorithm","method_name":"Griffin-Lim Algorithm"},{"method_slug":"highway-layer","method_name":"Highway Layer"},{"method_slug":"highway-network","method_name":"Highway Network"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"location-sensitive-attention","method_name":"Location Sensitive Attention"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"mixture-of-logistic-distributions","method_name":"Mixture of Logistic Distributions"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"residual-gru","method_name":"Residual GRU"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tacotron","method_name":"Tacotron"},{"method_slug":"tacotron-2","method_name":"Tacotron 2"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"wavenet","method_name":"WaveNet"},{"method_slug":"zoneout","method_name":"Zoneout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2010.04301","atlas_url":"https://app.syntology.ai/?focus=2010.04301","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.04301"}},"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/maum-ai/wavegrad2","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Garvit-32/Non-Attentive-Tacotron","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IMDxD/NonAttentiveTacotron","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/balan/text-to-speech","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindslab-ai/wavegrad2","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JoungheeKim/Non-Attentive-Tacotron","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6,"unverified":1},"by_repo_kind":{"listed":{"samples":7,"ran":6,"repositories":2}},"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":"cb38d9b9c8bab789","entry":"get_abspath","repo":"JoungheeKim/Non-Attentive-Tacotron","repo_kind":"listed","path":"tacotron/utils.py","file_url":"https://github.com/JoungheeKim/Non-Attentive-Tacotron/blob/HEAD/tacotron/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cb38d9b9c8bab789"}},{"code_sha256_prefix":"08d6a5b23b6ff882","entry":"get_mask_from_lengths","repo":"IMDxD/NonAttentiveTacotron","repo_kind":"listed","path":"src/model/utils.py","file_url":"https://github.com/IMDxD/NonAttentiveTacotron/blob/HEAD/src/model/utils.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":"08d6a5b23b6ff882"}},{"code_sha256_prefix":"ea26bcaea1557fe9","entry":"get_trellis","repo":"JoungheeKim/Non-Attentive-Tacotron","repo_kind":"listed","path":"build_aligned_info.py","file_url":"https://github.com/JoungheeKim/Non-Attentive-Tacotron/blob/HEAD/build_aligned_info.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ea26bcaea1557fe9"}},{"code_sha256_prefix":"a79e0b1cd209a59b","entry":"load_filepaths_and_text","repo":"IMDxD/NonAttentiveTacotron","repo_kind":"listed","path":"src/model/utils.py","file_url":"https://github.com/IMDxD/NonAttentiveTacotron/blob/HEAD/src/model/utils.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":"a79e0b1cd209a59b"}},{"code_sha256_prefix":"8ccc2e9689ef3ce4","entry":"load_wav_to_torch","repo":"IMDxD/NonAttentiveTacotron","repo_kind":"listed","path":"src/model/utils.py","file_url":"https://github.com/IMDxD/NonAttentiveTacotron/blob/HEAD/src/model/utils.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":"8ccc2e9689ef3ce4"}},{"code_sha256_prefix":"2ddca714d7ff5828","entry":"merge_repeats","repo":"JoungheeKim/Non-Attentive-Tacotron","repo_kind":"listed","path":"build_aligned_info.py","file_url":"https://github.com/JoungheeKim/Non-Attentive-Tacotron/blob/HEAD/build_aligned_info.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2ddca714d7ff5828"}},{"code_sha256_prefix":"499d76d1bd20ad71","entry":"backtrack","repo":"JoungheeKim/Non-Attentive-Tacotron","repo_kind":"listed","path":"build_aligned_info.py","file_url":"https://github.com/JoungheeKim/Non-Attentive-Tacotron/blob/HEAD/build_aligned_info.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"499d76d1bd20ad71"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}