Statistical parametric speech synthesis with joint estimation of acoustic and excitation model parameters

By Ranniery da S. Maia, Heiga Zen, Mark John Francis Gales. 2010

22 citations recorded by the source corpus.

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. Heiga Zen
3. Yoshua Bengio
4. Kyunghyun Cho
5. Oriol Vinyals
6. Li Deng
7. Andrew W. Senior
8. Yoav Goldberg

In Speech & Audio

1. Junichi Yamagishi
2. Tomoki Toda
3. Sheng Zhao
4. Lei He
5. Heiga Zen
6. Xu Tan
7. Yanqing Liu
8. Frank K. Soong

Citations in the corpus

• WaveNet: A Generative Model for Raw Audio (2016, background): “There have been attempts to integrate these two steps into a single one (Toda & Tokuda, 2008; Wu & Tokuda, 2008; Maia et al., 2010; Nakamura et al., 2014; Muthukumar & Black, 2014; Tokuda & Zen, 2015; 2016; Takaki & Yamagishi, 2016).”
• Speech Synthesis Based on Hidden Markov Models (2013, methodology): “proposed a method that combines the extraction of spectral parameters and excitation signal modeling in a fashion similar to the factor analyzed trajectory HMM [149].”
• Directly modeling speech waveforms by neural networks for statistical parametric speech synthesis (2015, methodology): “…and acoustic model training into a single framework, e.g. the log spectral distortion-version of minimum generation error training (MGE­ LSD) [11], statistical vocoder (STAV OCO) [12], waveform-level statistical model [13], and mel-cepstral analysis-integrated hidden Markov models (HMMs) [14].”
• Directly modeling voiced and unvoiced components in speech waveforms by neural networks (2016, background): “There have been a couple of attempts to integrate acoustic feature extraction into acoustic modeling, such as the log spectral distortion-version of minimum generation error training [7], statistical vocoder [8], waveform-level statistical model [9], and melcepstral analysis-integrated hidden Markov”
• Integration of Spectral Feature Extraction and Modeling for HMM-Based Speech Synthesis (2014, methodology): “Although the proposed method treats the cepstral coefficients as probabilistic variables and estimate their distributions, the method in [21] uses only single cepstral coefficient vectors as an approximation.”
• RobuTrans: A Robust Transformer-Based Text-to-Speech Model (2020, methodology): “Owing to the development of deep learning techniques, modern TTS pipelines make a step from HMM-based statistical parametric TTS models (Maia, Zen, and Gales 2010), neural acoustic models (Ze, Senior, and Schuster 2013) to neural end-to-end TTS models (Wang et al. 2017; Shen et al. 2017; Li et al.…”