Conditional restricted Boltzmann machine for voice conversion
By Zhizheng Wu, Chng Eng Siong, Haizhou Li. 2013
84 citations recorded by the source corpus.
The conventional statistical-based transformation functions for voice conversion have been shown to suffer over-smoothing and over-fitting problems. The over-smoothing problem arises because of the statistical average during estimating the model parameters for the transformation function. In addition, the large number of parameters in the statistical model cannot be well estimated from the limited parallel training data, which will result in the over-fitting problem. In this work, we investigate a robust transformation function for voice conversion using conditional restricted Boltzmann machine. Conditional restricted Boltzmann machine, which performs linear and non-linear transformations simultaneously, is proposed to learn the relationship between source and target speech. CMU ARCTIC corpus is adopted in the experimental validations. The number of parallel training utterances is varied from 2 to 40. For these different training situations, two objective evaluation measures, mel-cepstral distortion and correlation coefficient, both show that the proposed method outperforms the main stream joint density Gaussian mixture model method consistently.
Subfields: Artificial Intelligence, 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
In Signal Processing
Citations in the corpus
- Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron (2018, methodology): “To perform voice conversion, a model must synthesize an utterance, given only the acoustic signal of that utterance in a different speaker’s voice (Wu et al., 2013; Nakashika et al., 2016; Kinnunen et al., 2017; van den Oord et al., 2017; Chorowski et al., 2017).”
- Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis (2018, background): “Style Transfer Style transfer is an active area of research that aims to synthesize a phrase in the prosodic style of a reference signal (Wu et al., 2013; Nakashika et al., 2016; Kinnunen et al., 2017).”
- Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data (2017, background): “Learning to disentangle the mixed information from the surface representation is essential for a wide variety of speech applications: for example, noise robust speech recognition [41, 38, 37, 16], speaker verification [5], and voice conversion [40, 29, 24].”
- Learning Latent Representations for Speech Generation and Transformation (2017, background): “Particularly, VAE addresses the intractability issue that occurs in even moderately complicated models such as Restricted Boltzmann machines (RBMs), which have been applied for voice conversion [9, 10, 11], and provides efficient approximated posterior inference of the latent factors.”
- An overview of voice conversion systems (2017, methodology): “Several other extensions of NMF approaches have been proposed, such as mapping the activation matrix ( AIHARA et al., 2015 ), many-to-many VC ( Aihara et al., 2015 ), including contextual information ( Wu et al., 2013c; 2014b; Benisty et al., 2014 ), and local linear embeddings ( Wu et al., 2016 ).”
- Emotional voice conversion using deep neural networks with MCC and F0 features (2016, methodology): “There are also some approaches to construct non-linear mapping relationships, such as using artificial neural networks (ANNs) to train the mapping dictionaries between source and target features [11], using a conditional restricted Boltzmann machine (CRBM) to model the conditional distributions [12]”
- Voice Conversion Using Deep Neural Networks With Layer-Wise Generative Training (2014, methodology): “However, there are several problems with the classical joint density GMM (JDGMM)-based spectral conversion method.”