TY - JOUR AU - Li, Naihan AU - Liu, Shujie AU - Liu, Yanqing AU - Zhao, Sheng AU - Liu, Ming PY - 2019/07/17 Y2 - 2024/03/29 TI - Neural Speech Synthesis with Transformer Network JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 33 IS - 01 SE - AAAI Technical Track: Natural Language Processing DO - 10.1609/aaai.v33i01.33016706 UR - https://ojs.aaai.org/index.php/AAAI/article/view/4642 SP - 6706-6713 AB - <p>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).</p> ER -