Abstract
In this paper, we present a voice conversion (VC) method that does not use any parallel data while training the model. Voice conversion is a technique where only speaker-specific information in the source speech is converted while keeping the phonological information unchanged. Most of the existing VC methods rely on parallel data—pairs of speech data from the source and target speakers uttering the same sentences. However, the use of parallel data in training causes several problems: (1) the data used for the training is limited to the pre-defined sentences, (2) the trained model is only applied to the speaker pair used in the training, and (3) a mismatch in alignment may occur. Although it is generally preferable in VC to not use parallel data, a non-parallel approach is considered difficult to learn. In our approach, we realize the non-parallel training based on speaker-adaptive training (SAT). Speech signals are represented using a probabilistic model based on the Boltzmann machine that defines phonological information and speaker-related information explicitly. Speaker-independent (SI) and speaker-dependent (SD) parameters are simultaneously trained using SAT. In the conversion stage, a given speech signal is decomposed into phonological and speaker-related information, the speaker-related information is replaced with that of the desired speaker, and then voice-converted speech is obtained by combining the two. Our experimental results showed that our approach outperformed the conventional non-parallel approach regarding objective and subjective criteria.
Highlights
In recent years, voice conversion (VC), which is a technique used to change speaker-specific information in the speech of a source speaker into that of a target speaker while retaining linguistic information, has been garnering much attention since the VC techniques can be applied to various tasks [1,2,3,4,5]
5.4 Evaluation using various speaker pairs We investigated the performance of the proposed speaker adaptive trainable Boltzmann machine (SATBM) using various speaker pairs that include four gender types: male-to-female (M2F), female-to-male (F2M), male-to-male (M2M), and female-to-female (F2F)
When we compare the VC performance of different speaker pairs using the Mel-cepstral distortion (MCD), we may conclude that the model performed best when converting “ECL0001” to “MIT0001” because this conversion provided the smallest MCD
Summary
Voice conversion (VC), which is a technique used to change speaker-specific information in the speech of a source speaker into that of a target speaker while retaining linguistic information, has been garnering much attention since the VC techniques can be applied to various tasks [1,2,3,4,5]. Most of the existing approaches rely on statistical models [6, 7], and the approach based on the Gaussian mixture model (GMM) [8,9,10,11] is one of the mainstream methods used nowadays. Other statistical models, such as non-negative matrix factorization (NMF) [12, 13], neural networks (NNs) [14], restricted Boltzmann machines (RBMs) [15, 16], and deep learning [17, 18], are used in VC. The multistep VC [24] is proposed to reduce the training cost of estimating the mapping functions for each speaker pair
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: EURASIP Journal on Audio, Speech, and Music Processing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
