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.”
Method
Cited by
Sorted by citations
Items 701–753 of 753
Arya, L., & Prasanna, S. R. M. (2025) · National Conference on Communications · doi:10.1109/ncc63735.2025.10983860 · Cited by 1
Systematic Analysis of Effectiveness of Artificial Data in Direct Speech-to-Speech Translation
Arya, L., & Prasanna, S. R. M. (2025) · National Conference on Communications · doi:10.1109/ncc63735.2025.10983042
Multigranular Unified Synthesis Encoder for Fine-grained Multimodal Emotion UnderstandingPreprint
Ray, C., Nasir, W., & Grace, S. (2025) · Preprints.org · doi:10.20944/preprints202505.1230.v1
Zero-Voice: A Low-Resource Approach For Zero-shot Text-to-SpeechPreprint
Wang, Z., Hou, F., & Wang, R. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.6590685
Neural TTS-Based Dynamic Data Augmentation for Improved Speech Separation
Wang, K., Zhu, C., Yin, L., Li, S., Mansurova, M., & Huang, H. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3578779
Mehra, S. (2025) · International Journal of Computer Applications · doi:10.5120/ijca2025925146
Disentangling Segmental and Prosodic Factors to Non-Native Speech Comprehensibility
Quamer, W., & Gutiérrez‐Osuna, R. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3592320
Explainability of Language Models (XAI and LLM)
Cecco, A. D., & Gianfagna, L. (2025) · Springer eBooks · doi:10.1007/978-3-031-92229-9_8
Challenges and Opportunities of Generative Ai Models in Audio/AcousticPreprint
Dibbo, S. V., Lin, C.-H., & Vhaduri, S. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5404604
Audio-deepfake: Generation Methods, Legitimate Applications and the Potential for Misuse
Bendiab, G., Zeltni, K., Bader-El-Den, M. B., & Shiaeles, S. N. (2025) · IEEE International Conference on Cyber Security and Resilience (CSR) · doi:10.1109/csr64739.2025.11130020 · Cited by 1
Yao, W., Fen, X., Xiao, Y., Li, Z., Chen, X., & Wen, W. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04549-2_15
ITransformer_CNN: a malicious DNS detection method with flexible feature extraction
Zhang, W., Chen, W., Zhang, Z., Zhang, F., & Wu, L. (2022) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-025-02122-5
Reddy, A. S. K., Lal, B., Bhaskar, K. A., Bhaskar, M., Ashish, A., & Bisen, D. (2025) · International Journal of Speech Technology · doi:10.1007/s10772-025-10205-0
BVTS: A High-Quality Speech Synthesis Model Enhanced by BERT
尹, 鹏. (2025) · Computer Science and Application · doi:10.12677/csa.2025.1511286
Wiguna, Y. T., Prihasto, B., Pratama, B. M., Yeh, C.-H., & Wang, J. (2025) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc65261.2025.11249180
Emotion-Rich Cross-Speaker TTS via Contrastive Prosody Enhancement
Chien, J., & Ngo, B. G. (2025) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc65261.2025.11249208
ECTSpeech: Enhancing Efficient Speech Synthesis via Easy Consistency Tuning
zhu, T., Yu, Y., Wang, L., Sun, F., & Zheng, W. (2025) · ACM International Conference on Multimedia in Asia (MMAsia) · doi:10.1145/3743093.3771028
Speech-Based Real-World Scene Understanding for Assistive Care of the Visually Impaired
Sunil, T., Vinod, K., Madhav, M., Abraham, J., & Lal, G. J. (2025) · Springer series in reliability engineering · doi:10.1007/978-3-031-98728-1_2
Zero-Voice: A Low-Resource Approach For Zero-shot Text-to-SpeechPreprint
Wang, R., Wang, Z., & Hou, F. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5954473
Severity-Controllable Pathological Text-to-Speech Synthesis for Clinical Applications
Halpern, B. M., Huang, W.-C., Violeta, L. P., & Toda, T. (2026) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2026.3651761
Emotional Speech Synthesis via Diffusion Transformer with Reference Audio Pool *
Shen, Q., & Yang, J. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342604
Using transformers to learn system models
Ibias, A., Méndez, M., Núñez, M., & Palomo‐Lozano, F. (2026) · Applied Intelligence · doi:10.1007/s10489-025-07066-0
Chan, D.-Y., Zhong, J.-H., Wang, J.-F., & Tsai, H.-C. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21200-1
A didactic overview of Transformer applications: model variations and user guidelines
Cabrera-Bermejo, M. I., Germán, M., de la Rosa, D., Jesus, M. D., Rivera, A., Elizondo, D. A., Charte, F., & Godoy, P. (2025) · Logic Journal of IGPL · doi:10.1093/jigpal/jzaf040
Low Bit-Rate Speech Coding Based upon GMD-LPCNet
Zhang, C., & Wang, K. (2026) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-14681-6_9
AI-Powered Video Summarizer And Knowledge Assistant
Megala, R., Narayani, S., Srinidhi, P. S., Yalini, S., & Dhanushpriyan, S. (2025) · International Conference on Ubiquitous Computing and Intelligent Information Systems (ICUIS) · doi:10.1109/icuis67429.2025.11380591
UniDiff-TTS: Aligner-Free Diffusion Speech Synthesis with Duration Guidance
Chen, Y., Qi, Y., & Chen, W. (2025) · International Conference on Artificial Intelligence and Computer Engineering (ICAICE) · doi:10.1109/icaice68195.2025.11382398
Language Independent Phoneme Based Speech Transceiver for Limited Bandwidth Resource Communication
Rakesh, V. K., Pal, S., Das, A. K., & Samanta, T. (2026) · Lecture notes in networks and systems · doi:10.1007/978-981-96-9494-5_25
Comparative Analysis of Text-to-Speech Synthesis Systems
Kukreja, D., Tandon, A., Mehta, D., Bhatt, S., & Garg, G. (2025) · International Conference on Artificial Intelligence and Speech Technology (AIST) · doi:10.1109/aist68591.2025.11441499
Virtual Humans: A Survey of Technologies and Applications
Xu, Y., Zhang, W., Liu, Y., & Liu, J. (2025) · International Conference on Vision, Image and Signal Processing (ICVISP) · doi:10.1109/icvisp68610.2025.11451745
Self-citationRepresentation Learning and Deep Generative Modeling in Dynamical Systems
Franceschi, J.-Y. (2022) · theses.fr (ABES) · doi:10.70675/33a09a12zb431z4a33za503z8a867fe5657d
Expressivity transfer in deep learning based text-to-speech synthesis
Kulkarni, A. (2022) · theses.fr (ABES) · doi:10.70675/b44b847azf274z4851za996z397c3d49ca73
Sentence Embeddings for Massively Multilingual Speech and Text Processing
Duquenne, P.-A. (2024) · theses.fr (ABES) · doi:10.70675/8465c7cbzdf69z4d79z8950zb4a862100148
A lightweight bidirectional GRU–DCNN hybrid framework for end-to-end automatic speech recognition
Karthikeyan, V., Paramasivan, S., & Natchiyar, M. (2026) · Microsystem Technologies · doi:10.1007/s00542-025-05973-3
Mamba-Based Encoder for Multitask Joint Speech-Text Embeddings
Gonzales, M. G., Corcoran, P., & Schukat, M. (2026) · International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) · doi:10.1109/acdsa67686.2026.11468025
Conversational Image Recognition System to Comprehend an Image
Fathima, N., P, R. P. H., Prashanth, S., Vikas, B., & Prof. Chandrashekar, G. (2026) · International Conference on Visual Analytics and Data Visualization (ICVADV) · doi:10.1109/icvadv67766.2026.11470367
UniDiff-TTS: Aligner-Free Diffusion Speech Synthesis with Duration Guidance
Chen, Y., Qi, Y., & Chen, W. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461388
Wu, Y., Jung, J.-W., Shim, H.-J., Cheng, X., & Wang, X. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461279
A Review on Event-Augmented, Audio-Visual Distillation for MicroLip-Reading with Tiny Transformers
Mikayelyan, A., Kumar, S., & Mallick, P. K. (2026) · International Conference on Emerging Systems and Intelligent Computing (ESIC) · doi:10.1109/esic68176.2026.11496105
Real-Time Speech Enhancement for Dysarthria Individuals Using NLP and Deep Learning
Chindam, S., Gobika, R., Vijeyasri, T., & Oswald, C. (2026) · International Conference on Innovative Trends in Information Technology (ICITIIT) · doi:10.1109/icitiit68860.2026.11499673
Review of Automatic Text-to-Speech Synthesis Methods
O’Shaughnessy, D. D. (2026) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2026.3693972
A Vision Transformer-Based Hybrid Encryption Watermarking Algorithm for Medical Image Security
Fan, Y., Li, J., Bhatti, U. A., & -, Y. C. (2025) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait67930.2025.11522629
Deep Learning and Neural Networks for Humanizing Conversational AI
Kosimov, O., Aarthi, S., Ravikumar, R. N., Bakhshilloevich, S. D., Odilbekovich, R. B., & Masharipova, G. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-3361-8.ch002
Pozhidaev, M. S., Teplykh, E., & Danilov, S. I. (2025) · Macrosociolinguistics and Minority Languages · doi:10.22363/2949-5997-2025-3-2-131-145
Yue, H., Xu, W., Zhou, M., & Sun, H. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3709950
Lifelike avatars: a study on performance and resource requirements
Drobnjak, A., & Botički, I. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02508-2
Cheng, W., Lim, K. H., Yu, Y. P., & Lim, T. M. (2026) · International Conference on Intelligent Information Technology (ICIIT) · doi:10.1145/3805862.3805892
Sound effect synthesis from language-independent mimicry: a case study on explosion sounds
Takizawa, R., Hirai, S., Kanezaki, A., & Suda, H. (2026) · APSIPA Transactions on Signal and Information Processing · doi:10.1108/atsip-02-2026-0010
Löber, S., Kim, K. M., & Chen, X. (2026) · Computer Assisted Language Learning · doi:10.1080/09588221.2026.2737122
Liu, C., Fang, M., We, Z., Mao, S., Zhang, G., & Han, J. (2026) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2026.3739182
MaoSpeechNet: A Pre-Trained Framework for Text-to-Speech Synthesis in Mao Language
Adahrii, P., Majhi, M. K., & Saha, S. K. (2026) · International Conference on Intelligent Computing and Sustainable Innovations in Technology (IC-SIT) · doi:10.1109/ic-sit69723.2026.11735742
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
Ren, Y., Hu, C., Tan, X., Qin, T., Zhao, S., Zhao, Z., & Liu, T.-Y. (2020) · arXiv · doi:10.48550/arxiv.2006.04558 · Cited by 580
Self-citation
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
