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
Capstone project on speech morphing: A highlight to undergraduate education on signal processing
TL;DR: To strengthen the bridge between theory and practice by means of selected capstone projects, designed according to constructivist principles, a project tackles a large number of fundamental aspects of the discipline through a storyline that captivates the student during its execution.
Proceedings ArticleDOI
Many-to-many Voice Conversion Based on Multiple Non-negative Matrix Factorization
TL;DR: An exemplar-based Voice Conversion (VC) method using Non-negative Matrix Factorization (NMF), which is different from conventional statistical VC, and assumes that this method is flexible because it can adopt it to voice quality control or noise robust VC.
Proceedings ArticleDOI
Speaker adaptation using only vocalic segments via frequency warping.
TL;DR: This paper explores the possibility of adapting the whole statistical voice model using frequency warping (FW) based transformations trained exclusively with vowels and achieves reasonable results even when the adaptation data exhibit medium/low recording quality.
Book ChapterDOI
Voice Transformations for the Evaluation of Speaker Verification Systems
J. Ph. Goldman,Gérard Chollet +1 more
TL;DR: This paper tries to compare the performance of two speaker verification systems with a new methodology of assessment and finds that one of the systems outperforms the other in terms of quality and efficiency.
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.