Individuality-preserving Voice Conversion for Articulation Disorders Using Dictionary Selective Non-negative Matrix Factorization

Aihara, Ryo; Takiguchi, Tetsuya; Ariki, Yasuo

doi:10.3115/v1/w14-1905

Cited by 6 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the years, voice conversion frameworks have mostly focused on spectral conversion between source and target speakers [8,21]. In the sense of the statistical parametric approaches, such as Gaussian mixture model (GMM) [59] and exemplar based on nonnegative matrix factorization [1,63], SVC showed a success in the linear transformation of the spectral information. Nonlinear transformation approaches, such as hidden Markov models (HMMs) [49], deep belief networks (DBNs) [45] and restricted Boltzmann machines (RBMs) [46], have been also shown to be effective in modeling the relationship between source-target features more accurately.…”

Section: Introductionmentioning

confidence: 99%

Continuous vocoder applied in deep neural network based voice conversion

Al-Radhi

Csapó

Németh

2019

Multimed Tools Appl

View full text Add to dashboard Cite

In this paper, a novel vocoder is proposed for a Statistical Voice Conversion (SVC) framework using deep neural network, where multiple features from the speech of two speakers (source and target) are converted acoustically. Traditional conversion methods focus on the prosodic feature represented by the discontinuous fundamental frequency (F0) and the spectral envelope. Studies have shown that speech analysis/synthesis solutions play an important role in the overall quality of the converted voice. Recently, we have proposed a new continuous vocoder, originally for statistical parametric speech synthesis, in which all parameters are continuous. Therefore, this work introduces a new method by using a continuous F0 (contF0) in SVC to avoid alignment errors that may happen in voiced and unvoiced segments and can degrade the converted speech. Our contribution includes the following. (1) We integrate into the SVC framework the continuous vocoder, which provides an advanced model of the excitation signal, by converting its contF0, maximum voiced frequency, and spectral features. (2) We show that the feed-forward deep neural network (FF-DNN) using our vocoder yields high quality conversion. (3) We apply a geometric approach to spectral subtraction (GA-SS) in the final stage of the proposed framework, to improve the signal-to-noise ratio of the converted speech. Our experimental results, using two male and one female speakers, have shown that the resulting converted speech with the proposed SVC technique is similar to the target speaker and gives state-of-the-art performance as measured by objective evaluation and subjective listening tests.

show abstract

Section: Introductionmentioning

confidence: 99%

Continuous vocoder applied in deep neural network based voice conversion

Al-Radhi

Csapó

Németh

2019

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…Voice conversion (VC) has been widely used in many speech processing tasks, such as speaking assistance [1], speech enhancement [2] and other applications [3], [4]. Therefore, the need for this type of technology in various fields has continued to propel related studies each year.…”

Section: Introductionmentioning

confidence: 99%

Emotional Voice Conversion with Adaptive Scales F0 Based on Wavelet Transform Using Limited Amount of Emotional Data

et al. 2017

Self Cite

View full text Add to dashboard Cite

Deep learning techniques have been successfully applied to speech processing. Typically, neural networks (NNs) are very effective in processing nonlinear features, such as mel cepstral coefficients (MCC), which represent the spectrum features in voice conversion (VC) tasks. Despite these successes, the approach is restricted to problems with moderate dimension and sufficient data. Thus, in emotional VC tasks, it is hard to deal with a simple representation of fundamental frequency (F0), which is the most important feature in emotional voice representation, Another problem is that there are insufficient emotional data for training. To deal with these two problems, in this paper, we propose the adaptive scales continuous wavelet transform (AS-CWT) method to systematically capture the F0 features of different temporal scales, which can represent different prosodic levels ranging from micro-prosody to sentence levels. Meanwhile, we also use the pre-trained conversion functions obtained from other emotional datasets to synthesize new emotional data as additional training samples for target emotional voice conversion. Experimental results indicate that our proposed method achieves the best performance in both objective and subjective evaluations.

show abstract

“…This technology can be widely applied in various application domains. For instances, emotion conversion [1], speaking assistance [2], and other applications [3] [4]. Therefore, the need for this type of technology in various fields has continued to propel related researches each year.…”

Section: Introductionmentioning

confidence: 99%

“…Among these approaches, a Gaussian Mixture Model (GMM) is widely used, and a number of improvements have been proposed [7] [8] for GMM-based voice conversion. Other VC methods, such as approaches based on non-negative matrix factorization (NMF) [9] [2] have also been proposed. The NMF and GMM methods are based on linear functions.…”

Section: Introductionmentioning

confidence: 99%

Emotional Voice Conversion Using Neural Networks with Different Temporal Scales of F0 based on Wavelet Transform

Luo¹,

Takiguchi²,

Ariki³

2016

9th ISCA Workshop on Speech Synthesis Workshop (SSW 9)

Self Cite

View full text Add to dashboard Cite

An artificial neural network is one of the most important models for training features of voice conversion (VC) tasks. Typically, neural networks (NNs) are very effective in processing nonlinear features, such as mel cepstral coefficients (MCC) which represent the spectrum features. However, a simple representation for fundamental frequency (F0) is not enough for neural networks to deal with an emotional voice, because the time sequence of F0 for an emotional voice changes drastically. Therefore, in this paper, we propose an effective method that uses the continuous wavelet transform (CWT) to decompose F0 into different temporal scales that can be well trained by NNs for prosody modeling in emotional voice conversion. Meanwhile, the proposed method uses deep belief networks (DBNs) to pretrain the NNs that convert spectral features. By utilizing these approaches, the proposed method can change the spectrum and the prosody for an emotional voice at the same time, and was able to outperform other state-of-the-art methods for emotional voice conversion.

show abstract

Individuality-preserving Voice Conversion for Articulation Disorders Using Dictionary Selective Non-negative Matrix Factorization

Cited by 6 publications

References 23 publications

Continuous vocoder applied in deep neural network based voice conversion

Continuous vocoder applied in deep neural network based voice conversion

Emotional Voice Conversion with Adaptive Scales F0 Based on Wavelet Transform Using Limited Amount of Emotional Data

Emotional Voice Conversion Using Neural Networks with Different Temporal Scales of F0 based on Wavelet Transform

Contact Info

Product

Resources

About