Open Access
Wavelet-based voice morphing
Christina Orphanidou,Irene M. Moroz,Stephen J. Roberts +2 more
- 01 Jan 2004
17
TL;DR: A new multi-scale voice morphing algorithm that enables a user to transform one person's speech pattern into another person's pattern with distinct characteristics, giving it a new identity, while preserving the original content.
read more
Abstract: This paper presents a new multi-scale voice morphing algorithm. This algorithm enables a user to transform one person's speech pattern into another person's pattern with distinct characteristics, giving it a new identity, while preserving the original content. The voice morphing algorithm performs the morphing at different subbands by using the theory of wavelets and models the spectral conversion using the theory of Radial Basis Function Neural Networks. The results obtained on the TIMIT speech database demonstrate effective transformation of the speaker identity.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A neural-wavelet architecture for voice conversion
Rodrigo Capobianco Guido,Lucimar Sasso Vieira,Sylvio Barbon Junior,Fabrício Lopes Sanchez,Carlos Dias Maciel,Everthon Silva Fonseca,José Carlos Pereira +6 more
TL;DR: This letter proposes a new architecture for voice conversion that is based on a joint neural-wavelet approach and examines the characteristics of many wavelet families to determine the one that best matches the requirements of the proposed system.
31
Complex Cepstrum Based Voice Conversion Using Radial Basis Function
TL;DR: The evaluation measures reveal that the proposed complex cepstrum based voice conversion system approximate the converted speech signal with better accuracy than the model based on the Mel cepStrum envelope based voice Conversion model with objective and subjective evaluations.
Cepstrum liftering based voice conversion using RBF and GMM
Jagannath Nirmal,Pramod Kachare,Suprava Patnaik,Mukesh A. Zaveri +3 more
- 03 Apr 2013
TL;DR: Low time and high time liftering is applied to the cepstrum to separate the vocal tract and glottal excitation of the speech signal and results indicate that the RBF based transformation can be used as an alternative to GMM based model.
8
A nonlinear transformation methods for GMM to improve over-smoothing effect
TL;DR: Nonlinear GMM-based transformation functions are proposed in an attempt to deal with the over-smoothing effects of linear transformation for voice processing to overcome the drawbacks of global nonlinear transformation functions.
7
Speech Pitch Shifting using Complex Continuous Wavelet Transform
Abhay Kumar,Renuka Jain +1 more
- 01 Sep 2006
TL;DR: This work has used complex wavelet transform to obtain and manipulate pitch of the signal, using wavelet 'pitch-scale' values which correspond to average pitch value of signal's voiced frame.
6
References
Voice conversion through vector quantization
Masanobu Abe,Satoshi Nakamura,Kiyohiro Shikano,Hisao Kuwabara +3 more
- 11 Apr 1988
TL;DR: The authors propose a new voice conversion technique through vector quantization and spectrum mapping which makes it possible to precisely control voice individuality.
564
Voice transformation using PSOLA technique
H. Valbret,Eric Moulines,J. P. Tubach +2 more
- 01 Jun 1992
TL;DR: A new system for voice conversion is described that combines a PSOLA (Pitch Synchronous Overlap and Add)-derived synthesizer and a module for spectral transformation, which produces a satisfyingly natural “transformed” voice.
398
•Proceedings Article
Statistical methods for voice quality transformation
Yannis Stylianou,Olivier Cappé,Eric Moulines +2 more
- 01 Jan 1995
TL;DR: This paper introduces a novel statistical method using Gaussian mixture models to learn spectral parameter correspondences between speakers, outperforming vector quantization-based techniques in efficiency and robustness for voice quality transformation.
123
•Proceedings Article
Subband based voice conversion.
Oytun Türk,Levent M. Arslan +1 more
- 01 Jan 2002
TL;DR: A new voice conversion method that improves the quality of the voice conversion output at higher sampling rates is proposed and is demonstrated by both subjective listening tests and applications to film dubbing and looping.
56
Estimation of speech embedded in a reverberant and noisy environment by independent component analysis and wavelets
TL;DR: This paper develops a system for enhancement of the speech signal with highest energy from a linear convolutive mixture of n statistically independent sound sources recorded by m microphones, where m
47