DNN-based stochastic postfilter for HMM-based speech synthesis

By Linghui Chen, Tuomo Raitio, Cassia Valentini-Botinhao, Junichi Yamagishi, Zhenhua Ling. 2014

41 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 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. Junichi Yamagishi
2. Tomoki Toda
3. Satoshi Nakamura
4. Sakriani Watiasri Sakti
5. Shinji Takaki
6. Graham Neubig
7. Alan W. Black
8. Hirokazu Kameoka

In Computer Vision and Pattern Recognition

1. Graham Neubig
2. Satoshi Nakamura
3. Alan W. Black
4. Junichi Yamagishi
5. Kunio Kashino
6. Tomoki Toda
7. Sakriani Watiasri Sakti
8. Hirokazu Kameoka

In Signal Processing

1. Junichi Yamagishi
2. Tomoki Toda
3. Shinji Takaki
4. Alan W. Black
5. Hirokazu Kameoka
6. Sakriani Watiasri Sakti
7. Satoshi Nakamura
8. Takuhiro Kaneko

Citations in the corpus

• A deep auto-encoder based low-dimensional feature extraction from FFT spectral envelopes for statistical parametric speech synthesis (2016, methodology): “The linguistic features and spectral envelopes in the training data were pre-normalized for training DNNs.”
• Postfilters to Modify the Modulation Spectrum for Statistical Parametric Speech Synthesis (2016, background): “Whereas conventional post-filtering processes [47], [55], [56], [57] requires the rule-based design [47], or manual tuning [55], the proposed post-filters enable automatic design and tuning.”
• Generative adversarial network-based postfilter for statistical parametric speech synthesis (2016, methodology): “A previous work [14, 15, 16] tried to represent it using a learning-based approach similar to ours, but they assumed its distribution as Gaussian (Chen et al.”