HMM-based statistical speech synthesis method is not requiring a very large speech corpus for training the system. In this system, statistical modeling is applied to learn distributions of context-dependent acoustic vectors extracted from speech signals, each vector containing a suitable parametric representation of one speech frame and Vietnamese phonetic rules to synthesize speech. The method...

Incremental speech synthesis aims at delivering the synthetic voice while the sentence is still being typed. The main challenges are the online estimation of the target prosody from a partial knowledge of the sentence’s syntactic structure, the online phonetization and estimation of parts of speech and the timing of the delivery. This thesis aims at solving these challenges resulting in the imp...

In this paper, we evaluate a framework of statistical parametric speech synthesis based on Gaussian process regression (GPR) and compare it with those based on hidden Markov model (HMM) and deep neural network (DNN). Recently, for the purpose of improving the performance of HMM-based speech synthesis, novel frameworks using deep architectures have been proposed and have shown their effectivenes...

In recent years, sub−band speech recognition has been found useful in robust speech recognition, especially for speech signals contaminated by band−limited noise. In sub−band speech recognition, full band speech is divided into several frequency sub−bands and then sub−band feature vectors or their generated likelihoods by corresponding sub−band recognizers are combined to give the result of rec...

This paper describes an eigenvoice technique for an HMMbased speech synthesis system which can synthesize speech with various voice qualities. In the eigenvoice technique, which has successfully been applied to fast speaker adaptation in an HMM based speech recognition, a large number of speaker dependent HMM sets are represented by a few parameters through a dimensionality reduction technique,...

This paper describes an HMM-based speech synthesis system developed by the HTS working group for the Blizzard Challenge 2007. To further explore the potential of HMM-based speech synthesis, we incorporate new features in our conventional system which underpin a speaker-independent approach: speaker adaptation techniques; adaptive training for HSMMs; and full covariance modeling using the CSMAPL...

In real acoustic environments, humans communicate with each other through speech by focusing on the target speech among environmental sounds. We can easily identify the target sound from other environmental sounds. For hands-free speech recognition, the identification of the target speech from environmental sounds is imperative. This mechanism may also be important for a selfmoving robot to sen...

We describe a novel algorithm for recursive estimation of nonstationary acoustic noise which corrupts clean speech, and a successful application of the algorithm in the speech feature enhancement framework of noise-normalized SPLICE for robust speech recognition. The noise estimation algorithm makes use of a nonlinear model of the acoustic environment in the cepstral domain. Central to the algo...

There are two types of methods for tone recognition of continuous speech: one-step and two-step approaches. Two-step approaches need to identify the syllable boundaries firstly, while one-step approaches do not. Previous studies mostly focus on two-step approaches. In this paper, a one-step approach using Multi-space distribution HMM (MSD-HMM) is investigated. The F0, which only exists in voice...

For speaker verification systems, security against imposture is one of the most important problems, and many approaches to reducing false acceptance of impostors as well as false rejection of clients have been investigated. On the other hand, imposture using synthetic speech has not been considered. In this paper, we investigate imposture against speaker verification systems using synthetic spe...