Tacotron: character-to-spectrogram sequence-to-sequence synthesis

What changed

Trained a character-conditioned sequence-to-sequence acoustic model with spectrogram reconstruction to simplify feature-engineered text-to-speech pipelines.

Scientific scope

Trained a character-conditioned sequence-to-sequence acoustic model with spectrogram reconstruction to simplify feature-engineered text-to-speech pipelines. Inherits sequence-to-sequence attention and acoustic reconstruction; original waveform reconstruction is not the later Tacotron2 neural vocoder. End-to-end terminology does not imply absence of signal processing, paired data or all prior knowledge.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Inherits sequence-to-sequence attention and acoustic reconstruction; original waveform reconstruction is not the later Tacotron2 neural vocoder. End-to-end terminology does not imply absence of signal processing, paired data or all prior knowledge.

Contributors

• Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.

• Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction