the open
    research
    Contribute
    Back to the reading lists

    Language, speech & LLMs· 2017

    Tacotron: Towards End-to-End Speech Synthesis

    Yuxuan Wang (first author) · 2017

    Read the original

    arXiv 1703.10135OpenAlex W2963609956

    On the reading lists

    Why it matters

    Popularized sequence-to-sequence neural TTS directly from text to acoustic features.

    Condensed from the expert lists' notes.

    Reading it

    Difficulty: Intermediate

    Read this first: sequence-to-sequence models with attention.

    The record

    First released
    2017 (from arXiv 1703.10135)
    Citations
    2,110 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Score
    0.534 · computed rank 200 · consensus 0.84, must-read 1, citations percentile 0.378 (2010s · language), awards 0, existing lists 0.5. Method

    Editor's notes

    • Readability check: pass: Clear end-to-end text-to-speech with attention. (AI draft (Claude), not yet reviewed, 2026-10-29)

    Data sources

    Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.