Year: 2020
Type: conference-paper
Abstract: Targeting at both high efficiency and performance, we propose AlignTTS to predict the mel-spectrum in parallel. AlignTTS is based on a Feed-Forward Transformer which generates mel-spectrum from a sequence of characters, and the duration of each character is determined by a duration predictor. Instead of adopting the attention mechanism in Transformer TTS to align text to mel-spectrum, the alignment loss is presented to consider all possible alignments in training by use of dynamic programming. Experiments on the LJSpeech dataset show that our model achieves not only state-of-the-art performance which outperforms Transformer TTS by 0.03 in mean option score (MOS), but also a high efficiency which is more than 50 times faster than real-time.
Authors: Zhen Zeng, Jianzong Wang, Ning Cheng, Tian Xia, Jing Xiao
Institution: Ping An (China)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Keywords: text-to-speech, duration prediction, LJSpeech
Open Access status: green
Awards: G5138959851, G7027044845
OpenAlex ID: W3016136182
