Voice Conversion (VC) consists in modifying a source voice to a target speaker voice. In our approach, we modified only the Code excited linear Predictive (CELP) coder by introducing a pre-processing before the coder for the voice conversion. The decoder part of CELP was not modified. This allows maintaining the transmission rate. Our approach for conversion consists in separating the voiced an...

This paper describes a technique for controlling voice quality of synthetic speech using multiple regression hidden semi-Markov model (HSMM). In the technique, we assume that the mean vectors of output and state duration distribution of HSMM are modeled by multiple regression with a parameter vector called voice quality control vector. We first choose three features for controlling voice qualit...

In this paper, we describe a novel model training method for one-to-many eigenvoice conversion (EVC). One-to-many EVC is a technique for converting a specific source speaker’s voice into an arbitrary target speaker’s voice. An eigenvoice Gaussian mixture model (EVGMM) is trained in advance using multiple parallel data sets consisting of utterance-pairs of the source speaker and many pre-stored ...

Two speech processing systems have been developed for realtime and non-real-time voice conversion. Using the real-time processing the user can apply conversion during voice over IP (VoIP) calls imitating identity of a specified target speaker. Non-real-time processing system converts prerecorded audio books read by a professional reader imitating voice of the user. Both systems require some spe...

This paper presents a novel cross-language voice conversion (VC) method based on eigenvoice conversion (EVC). Crosslanguage VC is a technique for converting voice quality between two speakers uttering different languages each other. In general, parallel data consisting of utterance pairs of those two speakers are not available. To deal with this problem, we apply EVC to cross-language VC. First...

Voice conversion has been used in many applications. The methods based on vector quantization codebook and Gaussian mixture models need dynamic time warping on parallel sentence corpus for generating mapping functions. Recent study tries to use less training data, and even without parallel sentence corpus. This paper presents a voice conversion method without using parallel sentence corpus. It ...

The aim of voice conversion is to transform an utterance spoken by an arbitrary (source) speaker to that of a specific (target) speaker. Text-to-speech (TTS), speech-to-speech translation, mimicry generation and human-machine interaction systems are among the numerous applications which can be greatly benefited by having a voice conversion module. Generally voice conversion systems require para...

The goal of voice conversion is to transform a sentence said by one speaker, to sound as if another speaker had said it. The classical conversion based on a Gaussian Mixture Model and several other schemes suggested since, produce muffled sounding outputs, due to excessive smoothing of the spectral envelopes. To reduce the muffling effect, enhancement of the Global Variance (GV) of the spectral...

Technical voice forgery in the forensic area has led to several studies, mainly dealing with voice conversion. In the last decade, latests developments around voice synthesis have reached satisfactory intelligibility and quality levels. Moreover several web-based or standalone apps can be used for TTS. Nowadays, HMM-based synthetic voices can be built to fool biometric systems. Several authors ...

Many voice conversion algorithms are based on frame-wise mapping from source features into target features. This ignores the inherent temporal continuity that is present in speech and can degrade the subjective quality. In this paper, we propose to optimize the speech feature sequence after a frame-based conversion algorithm has been applied. In particular, we select the sequence of speech feat...