Fast DCTTS: Efficient Deep Convolutional Text-to-Speech
arXiv:2104.00624
Abstract
We propose an end-to-end speech synthesizer, Fast DCTTS, that synthesizes speech in real time on a single CPU thread. The proposed model is composed of a carefully-tuned lightweight network designed by applying multiple network reduction and fidelity improvement techniques. In addition, we propose a novel group highway activation that can compromise between computational efficiency and the regularization effect of the gating mechanism. As well, we introduce a new metric called Elastic mel-cepstral distortion (EMCD) to measure the fidelity of the output mel-spectrogram. In experiments, we analyze the effect of the acceleration techniques on speed and speech quality. Compared with the baseline model, the proposed model exhibits improved MOS from 2.62 to 2.74 with only 1.76% computation and 2.75% parameters. The speed on a single CPU thread was improved by 7.45 times, which is fast enough to produce mel-spectrogram in real time without GPU.
arXiv comment5 pages, 1 figure, to be published in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2021
References in corpus (6)
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
- Pruning Filters for Efficient ConvNets
- Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention
- Effective Use of Variational Embedding Capacity in Expressive End-to-End Speech Synthesis
- Neural Speech Synthesis with Transformer Network