The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods

Lorenzo-Trueba, Jaime; Yamagishi, Junichi; Toda, Tomoki; Saito, Daisuke; Villavicencio, Fernando; Kinnunen, Tomi; Ling, Zhen-Hua

doi:10.21437/odyssey.2018-28

Cited by 263 publications

(189 citation statements)

References 34 publications

Supporting

Mentioning

186

Contrasting

Unclassified

Order By: Relevance

“…We compared the proposed CC-GAN based method with two conventional approaches, i.e., the CycleGAN based VC [10] and the StarGAN based VC [18], using the VCC2018 corpus [20]. The speakers in the corpus consist of 6 males and 6 females.…”

Section: Methodsmentioning

confidence: 99%

Many-To-Many Voice Conversion Using Conditional Cycle-Consistent Adversarial Networks

Lee

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Voice conversion (VC) refers to transforming the speaker characteristics of an utterance without altering its linguistic contents. Many works on voice conversion require to have parallel training data that is highly expensive to acquire. Recently, the cycle-consistent adversarial network (CycleGAN), which does not require parallel training data, has been applied to voice conversion, showing the state-ofthe-art performance. The CycleGAN based voice conversion, however, can be used only for a pair of speakers, i.e., one-toone voice conversion between two speakers. In this paper, we extend the CycleGAN by conditioning the network on speakers. As a result, the proposed method can perform many-to-many voice conversion among multiple speakers using a single generative adversarial network (GAN). Compared to building multiple CycleGANs for each pair of speakers, the proposed method reduces the computational and spatial cost significantly without compromising the sound quality of the converted voice. Experimental results using the VCC2018 corpus confirm the efficiency of the proposed method.

show abstract

Section: Methodsmentioning

confidence: 99%

Many-To-Many Voice Conversion Using Conditional Cycle-Consistent Adversarial Networks

Lee

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…We used sprocket [32], an open-source implementation of GMM-based voice conversion [13]. It was used as a baseline in the 2018 Voice Conversion Challenge [36] and it thus gives us a solid anchor when comparing to other VC methods. We tuned the hyper parameters of the GMM conversion model on the internal validation set (see Section IV-A).…”

Section: B Gmm Whisper Conversionmentioning

confidence: 99%

Voice Conversion for Whispered Speech Synthesis

Cotescu

Drugman

Huybrechts

et al. 2020

IEEE Signal Process. Lett.

Self Cite

View full text Add to dashboard Cite

We present an approach to synthesize whisper by applying a handcrafted signal processing recipe and Voice Conversion (VC) techniques to convert normally phonated speech to whispered speech. We investigate using Gaussian Mixture Models (GMM) and Deep Neural Networks (DNN) to model the mapping between acoustic features of normal speech and those of whispered speech. We evaluate naturalness and speaker similarity of the converted whisper on an internal corpus and on the publicly available wTIMIT corpus. We show that applying VC techniques is significantly better than using rule-based signal processing methods and it achieves results that are indistinguishable from copy-synthesis of natural whisper recordings. We investigate the ability of the DNN model to generalize on unseen speakers, when trained with data from multiple speakers. We show that excluding the target speaker from the training set has little or no impact on the perceived naturalness and speaker similarity of the converted whisper. The proposed DNN method is used in the newly released Whisper Mode of Amazon Alexa.Index Terms-whispered speech conversion, voice conversion (VC), whispered text to speech (TTS).

show abstract

“…In the similarity question, the participant is asked to judge the similarity between the utterance generated by one VC system and a natural utterance spoken by the target speaker in a 4-point scale. The setup is the same as in VCC2018 [38].…”

Section: Voice Conversion Challenge 2018 Spoke Taskmentioning

confidence: 99%

Bootstrapping Non-Parallel Voice Conversion from Speaker-Adaptive Text-to-Speech

Luong

Yamagishi

2019

2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

Self Cite

View full text Add to dashboard Cite

Voice conversion (VC) and text-to-speech (TTS) are two tasks that share a similar objective, generating speech with a target voice. However, they are usually developed independently under vastly different frameworks. In this paper, we propose a methodology to bootstrap a VC system from a pretrained speaker-adaptive TTS model and unify the techniques as well as the interpretations of these two tasks. Moreover by offloading the heavy data demand to the training stage of the TTS model, our VC system can be built using a small amount of target speaker speech data. It also opens up the possibility of using speech in a foreign unseen language to build the system. Our subjective evaluations show that the proposed framework is able to not only achieve competitive performance in the standard intra-language scenario but also adapt and convert using speech utterances in an unseen language.

show abstract

The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods

Cited by 263 publications

References 34 publications

Many-To-Many Voice Conversion Using Conditional Cycle-Consistent Adversarial Networks

Many-To-Many Voice Conversion Using Conditional Cycle-Consistent Adversarial Networks

Voice Conversion for Whispered Speech Synthesis

Bootstrapping Non-Parallel Voice Conversion from Speaker-Adaptive Text-to-Speech

Contact Info

Product

Resources

About