ATR μ-talk speech synthesis system

By Yoshinori Sagisaka, N. Kaiki, N. Iwahashi, Katsuhiko Mimura. 1992

Subfields: Natural Language Processing, Speech & Audio

How researchers see this paper

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

In Natural Language Processing

1. Junichi Yamagishi
2. Tie-Yan Liu
3. Tao Qin
4. Xu Tan
5. Yoshua Bengio
6. Graham Neubig
7. Kyunghyun Cho
8. Heiga Zen

In Speech & Audio

1. Junichi Yamagishi
2. Xu Tan
3. Tao Qin
4. Tie-Yan Liu
5. Frank K. Soong
6. Heiga Zen
7. Sheng Zhao
8. Tomoki Toda

Citations in the corpus

• WaveNet: A Generative Model for Raw Audio (2016, methodology): “…to realize the speech synthesis part; non-parametric, example-based approach known as concatenative speech synthesis (Moulines & Charpentier, 1990; Sagisaka et al., 1992; Hunt & Black, 1996), and parametric, model-based approach known as statistical parametric speech synthesis (Yoshimura, 2002;…”
• A Survey on Neural Speech Synthesis (2021, methodology): “The early computer-based speech synthesis methods include articulatory synthesis [52, 294], formant synthesis [293, 5, 167, 168], and concatenative synthesis [247, 235, 291, 124, 26].”
• Neural Voice Cloning with a Few Samples (2018, background): “Compared to traditional unit-select speech synthesis (Sagisaka et al., 1992) and statistical parametric speech synthesis (Zen et al.”
• Optimising selection of units from speech databases for concatenative synthesis (1995, background): “A more general system is described here which deals with both English and Japanese and is designed to apply to other languages too.”
• An Overview of Voice Conversion and Its Challenges: From Statistical Modeling to Deep Learning (2020, background): “[154] because the synthesized waveform is formed of sound units directly from the target speaker [155].”
• Text-to-Speech Synthesis (2009, background): “A number of proposals were put forth in answer to these proble ms of managing larger databases of units, enabling selection within a class of units, coping with missing units and ensuring good joins [387], [327], [503], [234].”
• Automatically clustering similar units for unit selection in speech synthesis (1997, background): “[9], units are of variable length, giving rise to the term non-uniform unit synthesis.”
• The ATR Multilingual Speech-to-Speech Translation System (2006, background): “Among them, ATR, as one of the pioneers in corpus-based speech synthesis technology, has made major contributions to the progress of the technology through various studies, which led us to the development of two TTS systems, -talk [7] and CHATR [8].”
• Statistical Parametric Speech Synthesis (2007, methodology): “ATR -talk was the fi rst to demonstrate the effectiveness of the automatic selection of appropriate units (Sagisaka et al., 1992), then CHATR generalized these techniques to multiple languages and an automatic training scheme (Hunt and Black, 1996).”