Neural iTTS: Toward Synthesizing Speech in Real-time with End-to-end Neural Text-to-Speech Framework

By Tomoya Yanagita, Sakriani Watiasri Sakti, Satoshi Nakamura. 2019

17 citations recorded by the source corpus.

Real-time machine speech interpreters aim to mimic human in-terpreters that able to produce high-quality speech translations on the fly. It requires all system components, including speech recognition, machine translation, and text-to-speech (TTS), to perform incrementally before the speaker has spoken an entire sentence. For TTS, this poses problems as a standard framework commonly requires language-dependent contextual linguistics of a full sentence to produce a natural-sounding speech waveform. Existing studies of incremental TTS (iTTS) have mainly been conducted on a model based on hidden Markov model (HMM). Recently, end-to-end TTS based on a neural net has synthesized more natural speech than HMM-based systems. In this paper, we take an initial step to construct iTTS based on end-to-end neural framework (Neural iTTS) and investigate the effects of various incremental units on the quality of end-to-end neural speech synthesis in both English and Japanese.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Frank K. Soong
5. Xinyu Yang
6. Zhaoxi Mu
7. Yizhuo Dong
8. Sheng Zhao

Citations in the corpus

• A Survey on Neural Speech Synthesis (2021, methodology): “Streaming TTS [74, 217, 316, 399, 317, 231] synthesizes speech once some input tokens are comming, without waiting for the whole input sentence, which can also speed up inference.”
• What the Future Brings: Investigating the Impact of Lookahead for Incremental Neural TTS (2020, methodology): “This is in contradiction with [15] who did not report any difference between incremental and offline synthesis for such lookahead.”
• Review of end-to-end speech synthesis technology based on deep learning (2021, methodology): “To solve this problem, some researchers have proposed streaming incremental TTS systems [50, 133, 198, 235], which can output speech in real time while inputting text, because they only need to see a few characters or words to synthesize speech.”