Author:
Ding Yuntao,Cai Rangzhuoma,Gong Baojia
Abstract
Nowadays, Tibetan speech synthesis based on neural network has become the mainstream synthesis method. Among them, the griffin-lim vocoder is widely used in Tibetan speech synthesis because of its relatively simple synthesis.Aiming at the problem of low fidelity of griffin-lim vocoder, this paper uses WaveNet vocoder instead of griffin-lim for Tibetan speech synthesis.This paper first uses convolution operation and attention mechanism to extract sequence features.And then uses linear projection and feature amplification module to predict mel spectrogram.Finally, use WaveNet vocoder to synthesize speech waveform. Experimental data shows that our model has a better performance in Tibetan speech synthesis.
Reference13 articles.
1. Wang P,et al.Word embedding for recurrent neural network based TTS synthesis[C]//Proceedings of IEEE International Conference on Acoustics,2015:4879-4883.
2. Lipton Z.C,Berkowitz J,Elkan C. A critical review of recurrent neural networks for sequence learning[J].arXiv preprint arXiv:1506.00019,2015
3. Zen H,Sak H. Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis[C]//Proceedings of IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP),2015:4470-4474
4. Naihan Li, Shujie Liu, Yanqing Liu,et al. Neural Speech Synthesis with Transformer Network[J]. arXiv preprint arXiv:1809.08895v3,2019
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. A Comparative Study on End-to-End Speech Synthetic Units for Amdo-Tibetan Dialect;2022 5th International Conference on Pattern Recognition and Artificial Intelligence (PRAI);2022-08-19