One of the largest challenges in speaker recognition is dealing with speaker-emotion variability problem. Nowadays, compensation techniques are the main solutions to this problem. In these methods, all kinds of speakers’ emotion speech should be elicited thus it is not user-friendly in the application. Therefore the basic problem is how to get the distribution of speakers’ emotion speech and ho...

Automatic recognition of the speech of children is a challenging topic in computer-based speech recognition systems. Conventional feature extraction method namely Mel-frequency cepstral coefficient (MFCC) is not efficient for children’s speech recognition. This paper proposes a novel fuzzy-based discriminative feature representation to address the recognition of Malay vowels uttered by children...

Problem statement: Tone distortion in Thai languages can deteriorate not only the intelligibility of speech but also its naturalness. Therefore, the correctness of tone must be carefully taken into account in continuous speech synthesis. The preliminary work confronted this problem when applying HMM-based speech synthesis to Thai. Approach: This study presented a study on speaker-dependent and ...

Objectives: One of the most effective methods to describe speech disorders is the measurement of speech intelligibility. The speech intelligibility indicates the extent of acoustic signals that correctly speaker produces and hearer receives. The purpose of this study was to investigate the speech intelligibility in the Persian children with Down syndrome, age range was 3 to 5 years, who had spo...

In this paper, we propose a noise robust speech recognition method by combination of temporal domain singular value decomposition(SVD) based speech enhancement and Gaussian mixture model(GMM) based speech estimation. The bottleneck of GMM based approach is a noise estimation problem. For this noise estimation problem, we incorporated the adaptive noise estimation in GMM based approach. Furtherm...

Most of the present text-to-speech systems produce an acceptable quality speech output. Text-tospeech systems that are based on limited domain techniques produce speech that is close to human speech; however, they lack flexibility in that they cannot be used to synthesize words not in their own vocabulary. One approach of dealing with the flexibility problem is to use hybrid systems which combi...

Aiming at the problem of noise overestimation when classical single-channel speech enhancement method suppresses noise, on basis time-frequency mask is put forward to improve quality and separation. First, we estimate prior signal-to-noise ratio from noisy speech, calculate finally combine synthesis enhance speech. Adaptive combines IBM IRM avoid over-suppressing noise. In this paper, processed...

We study the synthesis problem for distributed architectures with a parametric number of finite-state components. Parameterized specifications arise naturally in a synthesis setting, but thus far it was unclear how to decide realizability and how to perform synthesis. Using a classical result from verification, we show that for specifications in LTL\X, parameterized synthesis of token ring netw...

A genetic algorithm was used to recover the dynamics of a model vocal tract from the speech ~ressure wave that it produced. The algorithm was generally successful in p.erf?rmmg ~he optimization n~cessary to do this inverse problem: a problem with sI~ficanc~m the psychology, bIology and technology of speech. A natural extension of thIS work IS to study speech learning using a classifier system t...

Most commercialized speech recognition systems that have a large capacity and high recognition rates are a type of speaker dependent isolated word recognition systems. In order to extend the scope of recognition, it is necessary to increase the number of words that are to be searched. However, it shows a problem that exhibits a decrease in the system performance according to the increase in the...