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
Journal ArticleDOI
Distinct Cortical Pathways for Music and Speech Revealed by Hypothesis-Free Voxel Decomposition
TL;DR: This analysis revealed six components, each with interpretable response characteristics despite being unconstrained by prior functional hypotheses, whose weighted combinations explained voxel responses throughout auditory cortex.
Journal ArticleDOI
Spectral Mapping Using Artificial Neural Networks for Voice Conversion
TL;DR: A voice conversion approach using an ANN model to capture speaker-specific characteristics of a target speaker is proposed and it is demonstrated that such a voice Conversion approach can perform monolingual as well as cross-lingual voice conversion of an arbitrary source speaker.
Journal ArticleDOI
An overview of voice conversion systems
TL;DR: An overview of real-world applications of VC systems, extensively study existing systems proposed in the literature, and discuss remaining challenges are provided.
Proceedings ArticleDOI
Voice conversion using Artificial Neural Networks
TL;DR: The results of voice conversion evaluated using subjective and objective measures confirm that ANNs perform better transformation than GMMs and the quality of the transformed speech is intelligible and has the characteristics of the target speaker.
Journal ArticleDOI
Voice Conversion Using Partial Least Squares Regression
TL;DR: A technique to combine PLS with GMMs, enabling the use of multiple local linear mappings in voice conversion and to low-pass filter the component posterior probabilities to improve the perceptual quality of the mapping.
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.