Development of HMM-based Indonesian Speech Synthesis

By Sakriani Watiasri Sakti, Ranniery da S. Maia, Shinsuke Sakai, Tohru Shimizu, Satoshi Nakamura. 2008

How researchers see this paper

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

In Speech & Audio

Citations in the corpus

VQVAE Unsupervised Unit Discovery and Multi-scale Code2Spec Inverter for Zerospeech Challenge 2019 (2019, background): “The source corpora of the surprise language are describe here [21, 22], and further details can be found here [3].”
Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks (2019, methodology): “We compare models on English data, and then apply the best models unaltered on the ZRSC’19 evaluation language, Indonesian, a low-resource Austronesian language widely used as a lingua franca [42, 43].”
The Zero Resource Speech Challenge 2019: TTS without T (2019, background): “The Surprise language is Indonesian, for which the corpora are derived from those developed in [22, 23].”
Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion (2019, methodology): “In the ZeroSpeech 2019 Challenge [19], we achieve 2 nd place in terms of low bitrate under a strong di-mension constraint on the Surprise Language [20][21] leader-board.”
Exploring TTS without T Using Biologically/Psychologically Motivated Neural Network Modules (ZeroSpeech 2020) (2020, methodology): “41 for the surprise language [27, 28], when the Maximum a Posteriori (MAP) classification is scored using the Levenshtein distance and contiguous classmate frames are merged (Table 2).”
Unsupervised Acoustic Unit Representation Learning for Voice Conversion using WaveNet Auto-encoders (2020, background): “The 2019 part of the ZeroSpeech 2020 challenge corpus contains two languages: English dataset for development and a surprise language [33, 34] dataset for test.”
Statistical Parametric Speech Synthesis (2007, background): “, 2008), Hebrew, Hindi, Hungarian (T́ oth and Ńemeth, 2008), Indonesian (Sakti et al., 2008), Irish, Japanese (Yoshimura et al.”
Transformer VQ-VAE for Unsupervised Unit Discovery and Speech Synthesis: ZeroSpeech 2020 Challenge (2020, background): “The source corpora for the surprise language are described here [20, 21], and further details can be found [1].”
Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge (2020, background): “Indonesian is a low-resource Austronesian language widely used as a lingua franca [36, 37].”
Cyclic Spectral Modeling for Unsupervised Unit Discovery into Voice Conversion with Excitation and Waveform Modeling (2020, methodology): “The dataset of the 2019-task [10] in ZSC 2020 (1)consisted of English and Surprise [29, 30] languages, where each has a subset of voice dataset and unit dataset.”