Pith. sign in

REVIEW 4 cited by

Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1712.05884 v2 pith:ZYVHMQVU submitted 2017-12-16 cs.CL

Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions

Jonathan Shen , Ruoming Pang , Ron J. Weiss , Mike Schuster , Navdeep Jaitly , Zongheng Yang , Zhifeng Chen , Yu Zhang
show 5 more authors
Yuxuan Wang RJ Skerry-Ryan Rif A. Saurous Yannis Agiomyrgiannakis Yonghui Wu
This is my paper
classification cs.CL
keywords wavenetspectrogramsarchitecturemodelnetworkspeechsynthesissystem
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

This paper describes Tacotron 2, a neural network architecture for speech synthesis directly from text. The system is composed of a recurrent sequence-to-sequence feature prediction network that maps character embeddings to mel-scale spectrograms, followed by a modified WaveNet model acting as a vocoder to synthesize timedomain waveforms from those spectrograms. Our model achieves a mean opinion score (MOS) of $4.53$ comparable to a MOS of $4.58$ for professionally recorded speech. To validate our design choices, we present ablation studies of key components of our system and evaluate the impact of using mel spectrograms as the input to WaveNet instead of linguistic, duration, and $F_0$ features. We further demonstrate that using a compact acoustic intermediate representation enables significant simplification of the WaveNet architecture.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. The Watermark Shortcut: How Provenance Marking Sabotages Audio Deepfake Detection

    cs.SD 2026-06 unverdicted novelty 8.0

    Watermarking only synthetic audio leads deepfake detectors to use the watermark as a spurious shortcut, causing generalization failure, evasion by removing watermarks, and false positives on watermarked real audio.

  2. RUSLAN: Russian Spoken Language Corpus for Speech Synthesis

    eess.AS 2019-06 unverdicted novelty 7.0

    RUSLAN is a 31-hour single-speaker Russian speech corpus for TTS containing 22200 annotated samples, with a baseline end-to-end model scoring 4.05 naturalness and 3.78 intelligibility on MOS tests.

  3. Mechanisms of Misgeneralization in Physical Sequence Modeling

    cs.LG 2026-05 unverdicted novelty 6.0

    Generative sequence models for physical tasks exhibit physical misgeneralization where local prediction errors propagate through physical measurements to distort aggregate distributions over quantities like distance o...

  4. Hierarchical Sequence to Sequence Voice Conversion with Limited Data

    eess.AS 2019-07 unverdicted novelty 4.0

    Hierarchical seq2seq model for parallel voice conversion pretrained as autoencoder on single-speaker data then adapted to limited multispeaker data, using mel spectrograms converted via wavenet vocoder.