Sorry, you need to enable JavaScript to visit this website.

FastDCTTS: Efficient Deep Convolutional Text-to-Speech

Citation Author(s):
Minsu Kang, Jihyun Lee, Simin Kim, Injung Kim
Submitted by:
Minsu Kang
Last updated:
24 June 2021 - 4:52am
Document Type:
Presentation Slides
Document Year:
2021
Event:
Presenters Name:
Minsu Kang
Paper Code:
4829

Abstract 

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.

up
0 users have voted:

Dataset Files

FastDCTTS presentation slide

(16)