Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions
Open accessThe DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
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.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“These models significantly reduced reliance on linguistic knowledge, thereby effectively lowering the technical barriers to high-quality speech synthesis.”
From Audio Deepfake Detection: What Has Been Achieved and What Lies Ahead (2025) · cites this paper as [42]
Experimental — accuracy not yet measured
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
(2014) · Cited by 33,419
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213
Bidirectional recurrent neural networks
Schuster, M., & Paliwal, K. K. (1997) · IEEE Transactions on Signal Processing · doi:10.1109/78.650093 · Cited by 10,172
Self-citationDavis, S., & Mermelstein, P. (1980) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/tassp.1980.1163420 · Cited by 5,465
WaveNet: a generative model for raw audio
Oord, A. V. D., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1609.03499 · Cited by 4,911
Signal estimation from modified short-time Fourier transform
Griffin, D., & Lim, J. (1984) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/tassp.1984.1164317 · Cited by 2,095
Attention-Based Models for Speech Recognition
Chorowski, J., Bahdanau, D., Serdyuk, D., Cho, K., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1506.07503 · Cited by 2,021
Tacotron: towards end-to-end speech synthesis
Wang, Y., Skerry-Ryan, R. J., Stanton, D., Wu, Y., Weiss, R. J., Jaitly, N., Yang, Z., Xiao, Y., Chen, Z., Bengio, S., et al. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-1452 · Cited by 1,746
Self-citation(1994) · Aston Publications Explorer (Aston University) · Cited by 1,245
Statistical parametric speech synthesis
Zen, H., Tokuda, K., & Black, A. W. (2009) · Speech Communication · doi:10.1016/j.specom.2009.04.004 · Cited by 1,195
Unit selection in a concatenative speech synthesis system using a large speech database
Hunt, A. J., & Black, A. W. (2002) · 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings · doi:10.1109/icassp.1996.541110 · Cited by 1,190
Speech parameter generation algorithms for HMM-based speech synthesis
Tokuda, K., Yoshimura, T., Masuko, T., Kobayashi, T., & Kitamura, T. (2002) · 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100) · doi:10.1109/icassp.2000.861820 · Cited by 999
Statistical parametric speech synthesis using deep neural networks
Zen, H., Senior, A., & Schuster, M. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6639215 · Cited by 809
Self-citationSalimans, T., Karpathy, A., Chen, X., & Kingma, D. P. (2017) · arXiv · doi:10.48550/arxiv.1701.05517 · Cited by 584
Taylor, P. (2009) · Cambridge University Press eBooks · doi:10.1017/cbo9780511816338 · Cited by 529
Speech Synthesis Based on Hidden Markov Models
Tokuda, K., Nankaku, Y., Toda, T., Zen, H., Yamagishi, J., & Oura, K. (2013) · Proceedings of the IEEE · doi:10.1109/jproc.2013.2251852 · Cited by 404
Deep Voice: Real-time Neural Text-to-Speech
Arık, S. Ö., Chrzanowski, M., Coates, A., Diamos, G., Gibiansky, A., Kang, Y., Li, X., Miller, J. J., Ng, A. Y., Raiman, J., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.07825 · Cited by 381
Parallel WaveNet: Fast High-Fidelity Speech Synthesis
van den Oord, A., Li, Y., Babuschkin, I., Simonyan, K., Vinyals, O., Kavukcuoglu, K., van den Driessche, G., Lockhart, E., Cobo, L. C., Stimberg, F., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.10433 · Cited by 330
(2017) · International Conference on Learning Representations · Cited by 314
Deep voice 3: scaling text-to-speech with convolutional sequence learning
Ping, W., Peng, K., Gibiansky, A., Arik, S. O., Kannan, A., Narang, S., Raiman, J., & Miller, J. (2017) · arXiv · doi:10.48550/arxiv.1710.07654 · Cited by 313
Automatically clustering similar units for unit selection in speech synthesis
Black, A. W., & Taylor, P. (1997) · 5th European Conference on Speech Communication and Technology (Eurospeech 1997) · doi:10.21437/eurospeech.1997-219 · Cited by 282
Speaker-Dependent WaveNet Vocoder
Tamamori, A., Hayashi, T., Kobayashi, K., Takeda, K., & Toda, T. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-314 · Cited by 269
Deep Voice 2: Multi-Speaker Neural Text-to-Speech
Arık, S. Ö., Diamos, G., Gibiansky, A., Miller, J. J., Peng, K., Ping, W., Raiman, J., & Zhou, Y. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.08947 · Cited by 206
Zen, H., Agiomyrgiannakis, Y., Egberts, N., Henderson, F., & Szczepaniak, P. (2016) · Interspeech 2016 · doi:10.21437/interspeech.2016-522 · Cited by 102
Recent Advances in Google Real-Time HMM-Driven Unit Selection Synthesizer
Gonzalvo, X., Tazari, S., Chan, C.-A., Becker, M., Gutkin, A., & Silén, H. (2016) · Interspeech · doi:10.21437/interspeech.2016-264 · Cited by 62
Research works printed but not linked: 3
- ping, 2017, Deep voice 3: 2000-speaker neural text-to-speech, CoRR, abs 1710 7654
- schuster, 1999, On Supervised Learning from Sequential Data with Applications for Speech Recognition
- krueger, 2017, Zone out: Regularizing RNNs by randomly preserving hidden activations, Proc ICLR
Cited by
“Waveglow: a flow-based generative network for speech synthesis,”
Prenger, R., Valle, R., & Catanzaro, B. (2019) · ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2019.8683143 · Cited by 1,004
Speech synthesis from neural decoding of spoken sentences
Anumanchipalli, G. K., Chartier, J., & Chang, E. F. (2019) · Nature · doi:10.1038/s41586-019-1119-1 · Cited by 883
Deep Learning for Audio Signal Processing
Purwins, H., Li, B., Virtanen, T., Schluter, J., Chang, S.-Y., & Sainath, T. (2019) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2019.2908700 · Cited by 855
Yamamoto, R., Song, E., & Kim, J.-M. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9053795 · Cited by 827
LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech
Zen, H., Dang, V., Clark, R., Zhang, Y., Weiss, R. J., Jia, Y., Chen, Z., & Wu, Y. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-2441 · Cited by 752
Self-citation
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
- green
- arxiv.org
- 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
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.