Evaluation of methods for parameteric formant transformation in voice conversion

Turajlić, Emir; Rentzos, Dimitrios; Vaseghi, Saeed; Ho, Ching-Hsiang

doi:10.1109/icassp.2003.1198883

Cited by 9 publications

(9 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…aspects of the speech that occur over timescales larger than individual phonemes, and the Mannerisms such as particular word choice or preferred phrases, or all kinds of other high-level behavioral characteristics. The formant structure and the vocal tract are represented by the overall spectral envelope shape of the signal, and thus are major features to be considered in voice transformation (Kain & Macon, 2001 (Abe et al (1988);Arslan (1999)), linear transformation (Kain & Macon, 2001;Ye & Young, 2003), formant transformation (Turajlic et al, 2003), vocal tract length normalization (VTLN) (Sundermann et al, 2003), and prosodic transformation (Erro et al, 2010). In text-independent voice conversion techniques, the system trains on source and target speakers uttering different text.…”

Section: Voice Transformationmentioning

confidence: 99%

Audio-Visual Biometrics and Forgery

Greige¹,

Karam²

2011

Advanced Biometric Technologies

View full text Add to dashboard Cite

Section: Voice Transformationmentioning

confidence: 99%

Audio-Visual Biometrics and Forgery

Greige¹,

Karam²

2011

Advanced Biometric Technologies

View full text Add to dashboard Cite

“…In text-dependent methods, training procedures are based on parallel corpora, i.e., training data have the source and the target speakers uttering the same text. Such methods include vector quantization [2,7], linear transformation [38,84], formant transformation [77], vocal tract length normalization (VTLN) [71], and prosodic transformation [7]. In text-independent voice conversion techniques, the system is trained with source and target speakers uttering different texts.…”

Section: Speech Processingmentioning

confidence: 99%

“…Speaker transformation techniques [28,39,85,40,2,7,77,62,16] might involve modifications of different aspects of the speech signal that carries the speaker's identity. We can cite different methods.…”

Section: Speech Processingmentioning

confidence: 99%

Multimodal Human Machine Interactions in Virtual and Augmented Reality

Chollet

Esposito

Gentès

et al. 2009

Multimodal Signals: Cognitive and Algorithmic Issues

View full text Add to dashboard Cite

Abstract. Virtual worlds are developing rapidly over the Internet. They are visited by avatars and staffed with Embodied Conversational Agents (ECAs). An avatar is a representation of a physical person. Each person controls one or several avatars and usually receives feedback from the virtual world on an audio-visual display. Ideally, all senses should be used to feel fully embedded in a virtual world. Sound, vision and sometimes touch are the available modalities. This paper reviews the technological developments which enable audio-visual interactions in virtual and augmented reality worlds. Emphasis is placed on speech and gesture interfaces, including talking face analysis and synthesis.

show abstract

“…the lack of control of the spectral shape, has not been solved. Frequency warping methods, such as by Turajlic et al [9], give high quality of modified speech. However, frequency warping methods meet difficulties in modifying spectral peaks, such as preserving shapes of peaks, and emphasizing spectral peaks around 3 kHz in transformation of speaking voice into singing voice, since they do not estimate spectral peaks.…”

Section: Introductionmentioning

confidence: 99%

“…They can be classified into two popular approaches: linear prediction (LP)-based methods [7,8] and frequency warping methods [9]. LP-based methods are often affected by the pole interaction problem suffered by pole modification techniques.…”

Section: Introductionmentioning

confidence: 99%

A flexible spectral modification method based on temporal decomposition and Gaussian mixture model

Nguyen

Akagi

2009

Acoust. Sci. & Tech.

View full text Add to dashboard Cite

Manipulating spectral structure often leads to degradation of speech quality, which is mainly due to insufficient smoothness of the modified spectra between frames, and ineffective spectral modification. This paper presents a new spectral modification method to improve the quality of modified speech. If frames are processed independently, discontinuous features may be generated. Therefore, a speech analysis technique called temporal decomposition (TD), which decomposes speech into event targets and event functions, is used to model the spectral evolution effectively. Instead of modifying the speech spectra frame by frame, we only need to modify event targets and event functions. This feature leads to easy modification of the speech spectra, and the smoothness of modified speech is ensured by the shape of event functions. To improve spectral modification, we explore Gaussian mixture model parameters (spectral-GMM parameters) to model the spectral envelope of each event target, and develop a new algorithm for modifying spectral-GMM parameters in accordance with formant scaling factors. We first evaluate the effectiveness of our proposed method in spectra modeling, and then apply it to two areas which require different amounts of spectral modification, emotional speech synthesis and voice gender conversion. Experimental results show that the effectiveness of our proposed method is verified for spectra modeling and spectral modification.

show abstract

Evaluation of methods for parameteric formant transformation in voice conversion

Cited by 9 publications

References 5 publications

Audio-Visual Biometrics and Forgery

Audio-Visual Biometrics and Forgery

Multimodal Human Machine Interactions in Virtual and Augmented Reality

A flexible spectral modification method based on temporal decomposition and Gaussian mixture model

Contact Info

Product

Resources

About