Journal ArticleDOI
Voice transformation using PSOLA technique
H. Valbret,Eric Moulines,J. P. Tubach +2 more
- Vol. 11, Iss: 2, pp 175-187
Reads0
Chats0
TLDR
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.Abstract:
In this contribution, a new system for voice conversion is described. The proposed architecture combines a PSOLA (Pitch Synchronous Overlap and Add)-derived synthesizer and a module for spectral transformation. The synthesizer based on the classical source-filter decomposition allows prosodic and spectral transformations to be performed independently. Prosodic modifications are applied on the excitation signal using the TD-PSOLA scheme; converted speech is then synthesized using the transformed spectral parameters. Two different approaches to derive spectral transformations, borrowed from the speech-recognition domain, are compared: Linear Multivariate Regression (LMR) and Dynamic Frequency Warping (DFW). Vector-quantization is carried out as a preliminary stage to render the spectral transformations dependent of the acoustical realization of sounds. A formal listening test shows that the synthesizer produces a satisfyingly natural “transformed” voice. LMR proves yet to allow a slightly better conversion than DFW. Still there is room for improvement in the spectral transformation stage.read more
Citations
More filters
Proceedings ArticleDOI
Voice conversion based on Gaussian mixture modules with Minimum Distance Spectral Mapping
TL;DR: A new method for voice conversion called Minimum Distance Spectral Mapping (MDSM), based on a frequency-warped point-to-point mapping that robustly and accurately transforms formant frequencies while also maintaining spectral details is proposed.
Journal ArticleDOI
Multimodal voice conversion based on non-negative matrix factorization
TL;DR: This study proposes multimodal VC that improves the noise robustness of the authors' NMF-based VC method, and introduces the combination weight between audio and visual features and formulate a new cost function to estimate audio-visual exemplars.
Journal ArticleDOI
A novel method for voice conversion based on non-parallel corpus
TL;DR: A new algorithm for voice conversion is put forward which not only removes the necessity of parallel corpus in the training phase but also resolves the issue of insufficiency of the target speaker’s corpus.
Proceedings ArticleDOI
Voice conversion using conditional restricted Boltzmann machine
Fengyun Zhu,Ziye Fan,Xihong Wu +2 more
TL;DR: Experimental results show that short-term temporal structure could be modeled well by CRBM, and the proposed method outperforms conventional joint density Gaussian mixture models based method significantly.
Speech analysis – synthesis based on the ptdft for voice conversion
TL;DR: The method based on Pitch-Tracking modified Discrete Fourier Transform (PTDFT) is proposed with an idea to decom-pose speech signal into voiced and noise-like compo-nents, which can be consid-ered as an improvement of the model used in [2], and is successfully applied in speech coding framework.
References
More filters
Journal ArticleDOI
An Algorithm for Vector Quantizer Design
Y. Linde,A. Buzo,Robert M. Gray +2 more
TL;DR: An efficient and intuitive algorithm is presented for the design of vector quantizers based either on a known probabilistic model or on a long training sequence of data.
Book
Linear Prediction of Speech
John E. Markel,A. Gray +1 more
TL;DR: Speech Analysis and Synthesis Models: Basic Physical Principles, Speech Synthesis Structures, and Considerations in Choice of Analysis.
Journal ArticleDOI
Pitch-synchronous waveform processing techniques for text-to-speech synthesis using diphones
TL;DR: In a common framework several algorithms that have been proposed recently, in order to improve the voice quality of a text-to-speech synthesis based on acoustical units concatenation based on pitch-synchronous overlap-add approach are reviewed.
Proceedings ArticleDOI
Voice conversion through vector quantization
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.