Automatic discovery of a phonetic inventory for unwritten languages for statistical speech synthesis

By Prasanna Kumar Muthukumar, Alan W. Black. 2014

28 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Speech & Audio, Signal Processing

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. Wei-Ning Hsu
5. Emmanuel Dupoux
6. James R. Glass
7. Yi Ren
8. Satoshi Nakamura

In Speech & Audio

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Emmanuel Dupoux
5. Wei-Ning Hsu
6. Yi Ren
7. Sakriani Watiasri Sakti
8. Tomoki Toda

In Signal Processing

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Emmanuel Dupoux
5. Yi Ren
6. Wei-Ning Hsu
7. Sakriani Watiasri Sakti
8. Tomoki Hayashi

Citations in the corpus

• Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks (2019, background): “But, importantly, the task here involves unit discovery which compresses spoken input [23,24].”
• The Zero Resource Speech Challenge 2019: TTS without T (2019, background): “A limited number of papers have provided a proof of concept that TTS without T is feasible [3, 4].”
• UWSpeech: Speech to Speech Translation for Unwritten Languages (2020, background): “text. Therefore, the key to ease the speech translation for unwritten languages is to reduce the flexible continuous space of speech into a more restricted discrete space. A variety of previous works (Muthukumar and Black 2014; Chen et al. 2015; Wilkinson, Zhao, and Black 2016; Adams 2017; Kamper, Li”
• Cyclic Spectral Modeling for Unsupervised Unit Discovery into Voice Conversion with Excitation and Waveform Modeling (2020, background): “A lot of work have been proposed for the unsupervised discovery of subword units [3, 6, 8, 11, 12, 13].”
• Virtual Phone Discovery for Speech Synthesis Without Text (2019, methodology): “A text free synthesis approach for building such system was proposed by obtaining automatic transcriptions at phone level from the speech signals [14].”
• Postfilters to Modify the Modulation Spectrum for Statistical Parametric Speech Synthesis (2016, background): “A LTHOUGH human beings naturally utilize their own speech as a communication tool, there exist many barriers in speech communication, such as vocal disorders [1], [2], [3], language differences [4], [5], [6], and physical constraints [3], [7].”