{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/tacotron-2","slug":"tacotron-2","name":"Tacotron 2","full_name":"Tacotron2","full_name_withheld":false,"description_markdown":"**Tacotron 2** is a neural network architecture for speech synthesis directly from text. It consists of two components:\r\n\r\n- a recurrent sequence-to-sequence feature prediction network with\r\nattention which predicts a sequence of mel spectrogram frames from\r\nan input character sequence\r\n- a modified version of [WaveNet](https://paperswithcode.com/method/wavenet) which generates time-domain waveform samples conditioned on the\r\npredicted mel spectrogram frames\r\n\r\nIn contrast to the original [Tacotron](https://paperswithcode.com/method/tacotron), Tacotron 2 uses simpler building blocks, using vanilla [LSTM](https://paperswithcode.com/method/lstm) and convolutional layers in the encoder and decoder instead of [CBHG](https://paperswithcode.com/method/cbhg) stacks and [GRU](https://paperswithcode.com/method/gru) recurrent layers. Tacotron 2 does not use a “reduction factor”, i.e., each decoder step corresponds to a single spectrogram frame. Location-sensitive attention is used instead of [additive attention](https://paperswithcode.com/method/additive-attention).","description_state":"present","introduced_year":null,"introduced_by":{"title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","paper":"/paper/natural-tts-synthesis-by-conditioning-wavenet","first_author":"Jonathan Shen","n_authors":13,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/natural-tts-synthesis-by-conditioning-wavenet"},"source":{"url":"http://arxiv.org/abs/1712.05884v2","title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/NVIDIA/tacotron2/blob/185cd24e046cc1304b4f8e564734d2498c6e2e6f/model.py#L457","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Audio","area_id":"audio","collection":"Text-to-Speech Models","url":"/methods/category/text-to-speech-models","pwc_aliases":[]}],"n_papers_tagged":23,"archive_num_papers":23,"papers_newest_first":[{"paper":null,"slug":"training-universal-vocoders-with-feature","title":"Training Universal Vocoders with Feature Smoothing-Based Augmentation Methods for High-Quality TTS Systems","date":"2024-09-04","arxiv_id":"2409.02517","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-overview-of-text-to-speech-systems-and","title":"An overview of text-to-speech systems and media applications","date":"2023-10-22","arxiv_id":"2310.14301","n_code_links":0,"syntology":null},{"paper":null,"slug":"energy-based-models-for-speech-synthesis","title":"Energy-Based Models For Speech Synthesis","date":"2023-10-19","arxiv_id":"2310.12765","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-text-to-speech-synthesis-for","slug":"multilingual-text-to-speech-synthesis-for","title":"Multilingual Text-to-Speech Synthesis for Turkic Languages Using Transliteration","date":"2023-05-25","arxiv_id":"2305.15749","n_code_links":1,"syntology":null},{"paper":null,"slug":"armantts-single-speaker-persian-dataset","title":"ArmanTTS single-speaker Persian dataset","date":"2023-04-07","arxiv_id":"2304.03585","n_code_links":0,"syntology":null},{"paper":"/paper/facial-landmark-predictions-with-applications","slug":"facial-landmark-predictions-with-applications","title":"Facial Landmark Predictions with Applications to Metaverse","date":"2022-09-29","arxiv_id":"2209.14698","n_code_links":1,"syntology":null},{"paper":null,"slug":"zero-shot-long-form-voice-cloning-with","title":"Zero-Shot Long-Form Voice Cloning with Dynamic Convolution Attention","date":"2022-01-25","arxiv_id":"2201.10375","n_code_links":0,"syntology":null},{"paper":"/paper/itacotron-2-transfering-english-speech","slug":"itacotron-2-transfering-english-speech","title":"ITAcotron 2: Transfering English Speech Synthesis Architectures and Speech Features to Italian","date":"2021-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-sequence-to-sequence-speech-synthesis","title":"Neural Sequence-to-Sequence Speech Synthesis Using a Hidden Semi-Markov Model Based Structured Attention Mechanism","date":"2021-08-31","arxiv_id":"2108.13985","n_code_links":0,"syntology":null},{"paper":"/paper/neural-hmms-are-all-you-need-for-high-quality","slug":"neural-hmms-are-all-you-need-for-high-quality","title":"Neural HMMs are all you need (for high-quality attention-free TTS)","date":"2021-08-30","arxiv_id":"2108.13320","n_code_links":2,"syntology":null},{"paper":null,"slug":"ctrl-p-temporal-control-of-prosodic-variation","title":"Ctrl-P: Temporal Control of Prosodic Variation for Speech Synthesis","date":"2021-06-15","arxiv_id":"2106.08352","n_code_links":0,"syntology":null},{"paper":null,"slug":"vara-tts-non-autoregressive-text-to-speech","title":"VARA-TTS: Non-Autoregressive Text-to-Speech Synthesis based on Very Deep VAE with Residual Attention","date":"2021-02-12","arxiv_id":"2102.06431","n_code_links":0,"syntology":null},{"paper":"/paper/bidirectional-variational-inference-for-non","slug":"bidirectional-variational-inference-for-non","title":"Bidirectional Variational Inference for Non-Autoregressive Text-to-Speech","date":"2021-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"using-previous-acoustic-context-to-improve","title":"Using previous acoustic context to improve Text-to-Speech synthesis","date":"2020-12-07","arxiv_id":"2012.03763","n_code_links":0,"syntology":null},{"paper":"/paper/learning-speaker-embedding-from-text-to","slug":"learning-speaker-embedding-from-text-to","title":"Learning Speaker Embedding from Text-to-Speech","date":"2020-10-21","arxiv_id":"2010.11221","n_code_links":1,"syntology":null},{"paper":"/paper/non-attentive-tacotron-robust-and-1","slug":"non-attentive-tacotron-robust-and-1","title":"Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling","date":"2020-10-08","arxiv_id":"2010.04301","n_code_links":6,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/speedyspeech-efficient-neural-speech","slug":"speedyspeech-efficient-neural-speech","title":"SpeedySpeech: Efficient Neural Speech Synthesis","date":"2020-08-09","arxiv_id":"2008.03802","n_code_links":3,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["janvainer/speedyspeech"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/one-model-many-languages-meta-learning-for","slug":"one-model-many-languages-meta-learning-for","title":"One Model, Many Languages: Meta-learning for Multilingual Text-to-Speech","date":"2020-08-03","arxiv_id":"2008.00768","n_code_links":1,"syntology":null},{"paper":"/paper/flowtron-an-autoregressive-flow-based","slug":"flowtron-an-autoregressive-flow-based","title":"Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis","date":"2020-05-12","arxiv_id":"2005.05957","n_code_links":3,"syntology":{"ran":11,"of":19,"n_ran_checked":8,"n_instrument":3,"unverified":8,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","official":{"repos":["NVIDIA/flowtron"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"fully-hierarchical-fine-grained-prosody","title":"Fully-hierarchical fine-grained prosody modeling for interpretable speech synthesis","date":"2020-02-06","arxiv_id":"2002.03785","n_code_links":0,"syntology":null},{"paper":"/paper/probing-the-phonetic-and-phonological","slug":"probing-the-phonetic-and-phonological","title":"Probing the phonetic and phonological knowledge of tones in Mandarin TTS models","date":"2019-12-23","arxiv_id":"1912.10915","n_code_links":1,"syntology":null},{"paper":"/paper/mellotron-multispeaker-expressive-voice","slug":"mellotron-multispeaker-expressive-voice","title":"Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens","date":"2019-10-26","arxiv_id":"1910.11997","n_code_links":5,"syntology":null},{"paper":"/paper/natural-tts-synthesis-by-conditioning-wavenet","slug":"natural-tts-synthesis-by-conditioning-wavenet","title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","date":"2017-12-16","arxiv_id":"1712.05884","n_code_links":33,"syntology":{"ran":7,"of":7,"n_ran_checked":2,"n_instrument":5,"unverified":0,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":null}}],"papers_shown":23,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":23,"with_a_code_link":13,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":23,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":4,"papers_where_code_ran_first_page":"/method/tacotron-2/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/tacotron-2/papers/ran/1","json":"/method/tacotron-2/papers/ran/1.json","rows":4}],"tasks":[{"task":"/task/text-to-speech","name":"Text to Speech","papers":15},{"task":"/task/text-to-speech-1","name":"text-to-speech","papers":15},{"task":"/task/speech-synthesis","name":"Speech Synthesis","papers":14},{"task":"/task/text-to-speech-synthesis","name":"Text-To-Speech Synthesis","papers":4},{"task":"/task/decoder","name":"Decoder","papers":3},{"task":"/task/style-transfer","name":"Style Transfer","papers":2},{"task":"/task/voice-cloning","name":"Voice Cloning","papers":2},{"task":"/task/acoustic-modelling","name":"Acoustic Modelling","papers":1},{"task":"/task/all","name":"All","papers":1},{"task":"/task/audio-synthesis","name":"Audio Synthesis","papers":1},{"task":null,"name":"CPU","papers":1},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/disentanglement","name":"Disentanglement","papers":1},{"task":"/task/form","name":"Form","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/classification","name":"General Classification","papers":1},{"task":"/task/meta-learning","name":"Meta-Learning","papers":1},{"task":"/task/representation-learning","name":"Representation Learning","papers":1},{"task":"/task/rhythm","name":"Rhythm","papers":1},{"task":"/task/speaker-verification","name":"Speaker Verification","papers":1}],"tasks_shown":20,"n_tasks":26,"usage_by_year":[{"year":"2017","papers":1},{"year":"2019","papers":2},{"year":"2020","papers":7},{"year":"2021","papers":6},{"year":"2022","papers":2},{"year":"2023","papers":4},{"year":"2024","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/tacotron-2"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Tacotron%202","read_at":"2026-10-05T01:02:55+00:00","query":"Tacotron 2","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"1712.05884","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'Tacotron 2' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":[],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"a5b22b59d789680131471399a5443a7a92cee772bdb72a1302cdeec723355049","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}