One-to-Many and Many-to-One Voice Conversion Based on Eigenvoices

Toda, Tomoki; Ohtani, Yamato; Shikano, Kiyohiro

doi:10.1109/icassp.2007.367303

Cited by 72 publications

(47 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also describe one-to-many EVC [5] as a technique for flexibly controlling voice quality of the converted speech. This method consists of a training process, an adaptation process, and a conversion process.…”

Section: One-to-many Eigenvoice Conversion (Evc)mentioning

confidence: 99%

“…On the other hand, the EV-GMM for the aperiodic component estimation is trained using multiple joint feature vector sets consisting of the spectral segment features of the laryngectomee and the aperiodic components of the pre-stored non-laryngectomees. In this paper, we perform the PCA-based training method for the EV-GMM [5].…”

Section: Es-to-speech Based On One-to-many Evcmentioning

confidence: 99%

“…One weakness Copyright c 2010 The Institute of Electronics, Information and Communication Engineers of this conversion framework is that the voice quality of the converted speech comes from a target speaker who is not the laryngectomee. In order to allow the laryngectomee to flexibly control the converted voice quality, we further apply one-to-many eigenvoice conversion (EVC) [5] to ESto-Speech. One-to-many EVC is a technique for converting a specific source speaker's voice into an arbitrary target speaker's voice.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Esophageal Speech Enhancement Based on Statistical Voice Conversion with Gaussian Mixture Models

Doi

Nakamura

Toda

et al. 2010

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARYThis paper presents a novel method of enhancing esophageal speech using statistical voice conversion. Esophageal speech is one of the alternative speaking methods for laryngectomees. Although it doesn't require any external devices, generated voices usually sound unnatural compared with normal speech. To improve the intelligibility and naturalness of esophageal speech, we propose a voice conversion method from esophageal speech into normal speech. A spectral parameter and excitation parameters of target normal speech are separately estimated from a spectral parameter of the esophageal speech based on Gaussian mixture models. The experimental results demonstrate that the proposed method yields significant improvements in intelligibility and naturalness. We also apply one-to-many eigenvoice conversion to esophageal speech enhancement to make it possible to flexibly control the voice quality of enhanced speech.

show abstract

Section: One-to-many Eigenvoice Conversion (Evc)mentioning

confidence: 99%

Section: Es-to-speech Based On One-to-many Evcmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Esophageal Speech Enhancement Based on Statistical Voice Conversion with Gaussian Mixture Models

Doi

Nakamura

Toda

et al. 2010

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Following the same idea, eigenvoice-based conversion [11], and tensor representation of speaker space [12] are examples of similar successful attempts in voice conversion. However, these methods all require a Z. Wu and E. S. Chng are with the School of Computer Engineering, Nanyang Technological University, Singapore 639798, and also with Temasek Lab@NTU, Nanyang Technological University, Singapore.…”

Section: Introductionmentioning

confidence: 99%

Mixture of Factor Analyzers Using Priors From Non-Parallel Speech for Voice Conversion

Kinnunen

Chng

et al. 2012

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

Abstract-A robust voice conversion function relies on a large amount of parallel training data, which is difficult to collect in practice. To tackle the sparse parallel training data problem in voice conversion, this paper describes a mixture of factor analyzers method which integrates prior knowledge from nonparallel speech into the training of conversion function. The experiments on CMU ARCTIC corpus show that the proposed method improves the quality and similarity of converted speech. With both objective and subjective evaluations, we show the proposed method outperforms the baseline GMM method.Index Terms-Voice conversion, prior knowledge, factor analysis, mixture of factor analyzers.

show abstract

“…The trained conversion model makes it possible to convert the acoustic features of the source singer's singing voice into those of the target singer's singing voice in any song, keeping the linguistic information of the lyrics unchanged. Furthermore, to develop a more flexible SVC system, eigenvoice conversion (EVC) techniques [6] have been applied to SVC [7]. In an SVC system based on many-to-many EVC [8], which is one particular variety of EVC, an initial conversion model called the canonical eigenvoice GMM (EV-GMM) is trained in advance using multiple parallel data sets including song pairs of a single reference singer and many other singers.…”

Section: Introductionmentioning

confidence: 99%

Voice Timbre Control Based on Perceived Age in Singing Voice Conversion

Kobayashi

Toda

Doi

et al. 2014

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARYThe perceived age of a singing voice is the age of the singer as perceived by the listener, and is one of the notable characteristics that determines perceptions of a song. In this paper, we describe an investigation of acoustic features that have an effect on the perceived age, and a novel voice timbre control technique based on the perceived age for singing voice conversion (SVC). Singers can sing expressively by controlling prosody and voice timbre, but the varieties of voices that singers can produce are limited by physical constraints. Previous work has attempted to overcome this limitation through the use of statistical voice conversion. This technique makes it possible to convert singing voice timbre of an arbitrary source singer into those of an arbitrary target singer. However, it is still difficult to intuitively control singing voice characteristics by manipulating parameters corresponding to specific physical traits, such as gender and age. In this paper, we first perform an investigation of the factors that play a part in the listener's perception of the singer's age at first. Then, we applied a multiple-regression Gaussian mixture models (MR-GMM) to SVC for the purpose of controlling voice timbre based on the perceived age and we propose SVC based on the modified MR-GMM for manipulating the perceived age while maintaining singer's individuality. The experimental results show that 1) the perceived age of singing voices corresponds relatively well to the actual age of the singer, 2) prosodic features have a larger effect on the perceived age than spectral features, 3) the individuality of a singer is influenced more heavily by segmental features than prosodic features 4) the proposed voice timbre control method makes it possible to change the singer's perceived age while not having an adverse effect on the perceived individuality. key words: singing voice, voice conversion, perceived age, spectral and prosodic features, subjective evaluations

show abstract

One-to-Many and Many-to-One Voice Conversion Based on Eigenvoices

Cited by 72 publications

References 8 publications

Esophageal Speech Enhancement Based on Statistical Voice Conversion with Gaussian Mixture Models

Esophageal Speech Enhancement Based on Statistical Voice Conversion with Gaussian Mixture Models

Mixture of Factor Analyzers Using Priors From Non-Parallel Speech for Voice Conversion

Voice Timbre Control Based on Perceived Age in Singing Voice Conversion

Contact Info

Product

Resources

About