A Deep Learning Approach to Data-driven Parameterizations for Statistical Parametric Speech Synthesis
By Prasanna Kumar Muthukumar, Alan W. Black. 2014
6 citations recorded by the source corpus.
Nearly all Statistical Parametric Speech Synthesizers today use Mel Cepstral coefficients as the vocal tract parameterization of the speech signal. Mel Cepstral coefficients were never intended to work in a parametric speech synthesis framework, but as yet, there has been little success in creating a better parameterization that is more suited to synthesis. In this paper, we use deep learning algorithms to investigate a data-driven parameterization technique that is designed for the specific requirements of synthesis. We create an invertible, low-dimensional, noise-robust encoding of the Mel Log Spectrum by training a tapered Stacked Denoising Autoencoder (SDA). This SDA is then unwrapped and used as the initialization for a Multi-Layer Perceptron (MLP). The MLP is fine-tuned by training it to reconstruct the input at the output layer. This MLP is then split down the middle to form encoding and decoding networks. These networks produce a parameterization of the Mel Log Spectrum that is intended to better fulfill the requirements of synthesis. Results are reported for experiments conducted using this resulting parameterization with the ClusterGen speech synthesizer.
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
- Yoshua Bengio
- Junichi Yamagishi
- Quoc V. Le
- Oriol Vinyals
- Mohit Bansal
- Tie-Yan Liu
- Tao Qin
- Ruslan Salakhutdinov
In Speech & Audio
- Junichi Yamagishi
- Shinji Takaki
- Heiga Zen
- Xin Eric Wang
- Aäron van den Oord
- Tomoki Toda
- Zhenhua Ling
- Lei He
In Signal Processing
- Junichi Yamagishi
- Heiga Zen
- Tomoki Toda
- Aäron van den Oord
- Shinji Takaki
- Frank K. Soong
- Xu Tan
- Xin Eric Wang
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).”
- A deep auto-encoder based low-dimensional feature extraction from FFT spectral envelopes for statistical parametric speech synthesis (2016, methodology): “In the field of speech synthesis, similar auto-encoder based bottleneck features were tested for excitation parameters [22, 23] and statistical parametric speech synthesizers [24, 7].”