Student or educator? Sign up with your school email and get 6 months of Pro free.

The DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.

Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions

Open access

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 time-domain 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 conditioning input to WaveNet instead of linguistic, duration, and F0 features. We further show that using this compact acoustic intermediate representation allows for a significant reduction in the size of the WaveNet architecture.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/icassp.2018.8461368

Cites

29 of 29 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 29 references

Research works printed but not linked: 3

  1. ping, 2017, Deep voice 3: 2000-speaker neural text-to-speech, CoRR, abs 1710 7654
  2. schuster, 1999, On Supervised Learning from Sequential Data with Applications for Speech Recognition
  3. krueger, 2017, Zone out: Regularizing RNNs by randomly preserving hidden activations, Proc ICLR

Cited by

See all 2,791

Metadata

Authors
Shen, J., Pang, R., Weiss, R. J., Schuster, M., Jaitly, N., Yang, Z., Chen, Z., Zhang, Y., Wang, Y., Skerrv-Ryan, R., Saurous, R. A., Agiomvrgiannakis, Y., & Wu, Y.
Affiliations
  • Google (United States) (US)
  • University of California, Berkeley (US)
Venue
2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher
IEEE
Published
2018-04
Pages
4779-4783
ISSN
1520-6149 (ISSN-L)
OpenAlex
W2964243274
Cited by
2,791
References
29
Citations by year
2026: 212 · 2025: 293 · 2024: 304 · 2023: 371 · 2022: 430 · 2021: 494 · 2020: 377 · 2019: 231 · 2018: 76
FWCI
117.28
Type
conference paper
Language
en
Open access
Locations
  • IEEE International Conference on Acoustics Speech and Signal Processing (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
  • Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
  • Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
Keywords
Tacotron2, text-to-speech, character embeddings, waveform synthesis, synthetic speech quality, model size reduction

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions. https://app.cochat.ai/papers/10.1109/icassp.2018.8461368
The paper
Shen, J., Pang, R., Weiss, R. J., Schuster, M., Jaitly, N., Yang, Z., Chen, Z., Zhang, Y., Wang, Y., Skerrv-Ryan, R., Saurous, R. A., Agiomvrgiannakis, Y., & Wu, Y. (2018). Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp.2018.8461368

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.