Directly modeling voiced and unvoiced components in speech waveforms by neural networks

By Keiichi Tokuda, Heiga Zen. 2016

33 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing, 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. Yoshua Bengio
2. Quoc V. Le
3. Mohit Bansal
4. Ruslan Salakhutdinov
5. Oriol Vinyals
6. Sergey Levine
7. Kyunghyun Cho
8. Jianfeng Gao

In Natural Language Processing

1. Yoshua Bengio
2. Kyunghyun Cho
3. Oriol Vinyals
4. Yoav Goldberg
5. Quoc V. Le
6. Li Deng
7. Graham Neubig
8. Dong Yu

In Speech & Audio

1. Junichi Yamagishi
2. Heiga Zen
3. Aäron van den Oord
4. Karen Simonyan
5. Sander Dieleman
6. Oriol Vinyals
7. Lei He
8. Xin Eric Wang

In Signal Processing

1. Junichi Yamagishi
2. Heiga Zen
3. Aäron van den Oord
4. Sander Dieleman
5. Yu Zhang
6. Karen Simonyan
7. Dong Yu
8. Oriol Vinyals

Citations in the corpus

• WaveNet: A Generative Model for Raw Audio (2016, methodology): “As example-based and model-based speech synthesis base-lines, hidden Markov model (HMM)-driven unit selection concatenative (Gonzalvo et al., 2016) and long short-term memory recurrent neural network (LSTM-RNN)-based statistical parametric (Zen et al., 2016) speech synthesizers were built.”
• SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping (2022, background): “Some time-domain filters can be considered for the covariance matrix [38,39].”
• Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks (2017, methodology): “Also, we expect that our algorithm can be extended to waveform synthesis [44], [45].”