The DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.
Neural Speech Synthesis with Transformer Network
Open accessAbstract
Although end-to-end neural text-to-speech (TTS) methods (such as Tacotron2) are proposed and achieve state-of-theart performance, they still suffer from two problems: 1) low efficiency during training and inference; 2) hard to model long dependency using current recurrent neural networks (RNNs). Inspired by the success of Transformer network in neural machine translation (NMT), in this paper, we introduce and adapt the multi-head attention mechanism to replace the RNN structures and also the original attention mechanism in Tacotron2. With the help of multi-head self-attention, the hidden states in the encoder and decoder are constructed in parallel, which improves training efficiency. Meanwhile, any two inputs at different times are connected directly by a self-attention mechanism, which solves the long range dependency problem effectively. Using phoneme sequences as input, our Transformer TTS network generates mel spectrograms, followed by a WaveNet vocoder to output the final audio results. Experiments are conducted to test the efficiency and performance of our new network. For the efficiency, our Transformer TTS network can speed up the training about 4.25 times faster compared with Tacotron2. For the performance, rigorous human tests show that our proposed model achieves state-of-the-art performance (outperforms Tacotron2 with a gap of 0.048) and is very close to human quality (4.39 vs 4.44 in MOS).
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.
Integrity signals
Registry
Cites
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.
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?
In the citing paper
“Med-BERT [184] is a contextualized embedding model pretrained on a structured electronic health record dataset of two million patients.”
From Multimodal learning with transformers: A survey (2023) · cites this paper as [184]
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
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Jakubův, J., Chvalovský, K., Goertzel, Z., et al. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,648
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545
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
Error bounds for convolutional codes and an asymptotically optimum decoding algorithm
Viterbi, A. J. (1967) · IEEE Transactions on Information Theory · doi:10.1109/tit.1967.1054010 · Cited by 6,954
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
Self-Attention Generative Adversarial Networks
Zhang, H., Goodfellow, I., Metaxas, D., & Odena, A. (2018) · arXiv · doi:10.48550/arxiv.1805.08318 · Cited by 3,353
Convolutional Sequence to Sequence Learning
Gehring, J., Auli, M., Grangier, D., Yarats, D., & Dauphin, Y. N. (2017) · arXiv · doi:10.48550/arxiv.1705.03122 · Cited by 2,850 · cited 1×
“Previous NMT models are dominated by RNN-based (Bahdanau, Cho, and Bengio 2014) or CNN-based (e.g. ConvS2S (Gehring et al. 2017), ByteNet (Kalchbrenner et al. 2016)) neural networks.”
MethodNatural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions
Shen, J., Pang, R., Weiss, R. J., Schuster, M., Jaitly, N., Yang, Z., Chen, Z., Zhang, Y., Wang, Y., Skerrv-Ryan, R., et al. (2018) · 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2018.8461368 · Cited by 2,791
Signal estimation from modified short-time Fourier transform
Griffin, D. W., & Lim, J. S. (1984) · IEEE Transactions on Acoustics Speech and Signal Processing · doi:10.1109/tassp.1984.1164317 · Cited by 2,085
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
Unit selection in a concatenative speech synthesis system using a large speech database
Hunt, A., & Black, A. (1996) · 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings · doi:10.1109/icassp.1996.541110 · Cited by 1,508
Statistical parametric speech synthesis
Zen, H., Tokuda, K., & Black, A. W. (2009) · Speech Communication · doi:10.1016/j.specom.2009.04.004 · Cited by 1,202
Improving Variational Inference with Inverse Autoregressive FlowPreprint
Kingma, D., Salimans, T., Józefowicz, R., Chen, X., Sutskever, I., & Welling, M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.04934 · Cited by 1,168
Speech parameter generation algorithms for HMM-based speech synthesis
Tokuda, K., Yoshimura, T., Masuko, T., Kobayashi, T., & Kitamura, T. (2002) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2000.861820 · Cited by 1,004
Statistical parametric speech synthesis using deep neural networks
Zen, H., Senior, A., & Schuster, M. (2013) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2013.6639215 · Cited by 818
SampleRNN: An Unconditional End-to-End Neural Audio Generation ModelPreprint
Mehri, S., Kumar, K., Gulrajani, I., Kumar, R., Jain, S., Sotelo, J., Courville, A. C., & Bengio, Y. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.07837 · Cited by 551
Neural Machine Translation in Linear Time
Kalchbrenner, N., Espeholt, L., Simonyan, K., Oord, A. V. D., Graves, A., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1610.10099 · Cited by 414 · cited 1×
“Previous NMT models are dominated by RNN-based (Bahdanau, Cho, and Bengio 2014) or CNN-based (e.g. ConvS2S (Gehring et al. 2017), ByteNet (Kalchbrenner et al. 2016)) neural networks.”
MethodSpeech 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 408
Parallel WaveNet: Fast High-Fidelity Speech SynthesisPreprint
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 384
Verhelst, W., & Roelands, M. (1993) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.1993.319366 · Cited by 376
ClariNet: Parallel Wave Generation in End-to-End Text-to-SpeechPreprint
Ping, W., Peng, K., & Chen, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.07281 · Cited by 315
(2017) · International Conference on Learning Representations · Cited by 314
Automatically clustering similar units for unit selection in speech synthesis
Black, A. W., & Taylor, P. (1997) · European Conference on Speech Communication and Technology (Eurospeech) · doi:10.21437/eurospeech.1997-219 · Cited by 286
Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram PredictionsPreprint
Shen, J., Pang, R., Weiss, R. J., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.05884 · Cited by 185
Diphone synthesis using an overlap-add technique for speech waveforms concatenation
Charpentier, F., & Stella, M. (2005) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.1986.1168657 · Cited by 158
Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model.Preprint
Wang, Y., Skerry-Ryan, R., Stanton, D., Wu, Y., Weiss, R. J., Jaitly, N., Yang, Z., Xiao, Y., Chen, Z., Samy Bengio, A., et al. (2017) · arXiv (Cornell University) · Cited by 142
Tacotron: Towards End-to-End Speech SynthesisPreprint
Wang, Y., Skerry-Ryan, R., Stanton, D., Wu, Y., Weiss, R. J., Jaitly, N., Yang, Z., Xiao, Y., Chen, Z., Samy Bengio, A., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.10135 · Cited by 123
Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese
Zhou, S., Dong, L., Xu, S., & Xu, B. (2018) · Interspeech (USB) · doi:10.21437/interspeech.2018-1107 · Cited by 112
VoiceLoop: Voice Fitting and Synthesis via a Phonological LoopPreprint
Taigman, Y., Wolf, L., Polyak, A., & Nachmani, E. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.06588 · Cited by 68
Zhou, S., Dong, L., Xu, S., & Xu, B. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-04221-9_19 · Cited by 63
Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin ChinesePreprint
Zhou, S., Dong, L., Xu, S., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.10752 · Cited by 28
Zhou, S., Dong, L., Xu, S., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.06239 · Cited by 12
Flagged first, then by citations
Cited by
Sorted by citations
Taming Transformers for High-Resolution Image Synthesis
Esser, P., Rombach, R., & Ommer, B. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01268 · Cited by 2,514
Lin, T., Wang, Y., Liu, X., & Qiu, X. (2022) · AI Open · doi:10.1016/j.aiopen.2022.10.001 · Cited by 1,422
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech SynthesisPreprint
Kong, J., Kim, J., & Bae, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.05646 · Cited by 1,269
Multimodal learning with transformers: A survey
Xu, P., Zhu, X., & Clifton, D. A. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3275156 · Cited by 1,072
Yamamoto, R., Song, E., & Kim, J.-M. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9053795 · Cited by 867
Metadata
- Authors
- Li, N., Liu, S., Liu, Y., Zhao, S., & Liu, M.
- Affiliations
- University of Electronic Science and Technology of China (CN)
- Microsoft Research Asia (China) (CN)
- Microsoft (United States) (US)
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2019-07-17
- Volume
- 33
- Issue
- 01
- Pages
- 6706-6713
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W2903739847
- Cited by
- 754
- References
- 31
- Citations by year
- 2026: 28 · 2025: 88 · 2024: 103 · 2023: 131 · 2022: 138 · 2021: 165 · 2020: 89 · 2019: 11
- FWCI
- 38.55
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- www.aaai.org/ (unspecified)
- Locations
- Proceedings of the AAAI Conference on Artificial Intelligence (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (61572113)
- Fundamental Research Funds for the Central Universities (ZYGX2016J084, ZYGX2016J195, ZYGX2015J155, 61572113)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Health Sciences › Health Professions › Speech and Hearing › Voice and Speech Disorders
- Keywords
- neural text-to-speech, transformer models, multi-head self-attention, Tacotron2, long-range dependencies, mel-spectrogram generation, training efficiency, phoneme sequences
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
