This paper presents the beginnings of a framework for formal testing of the causes of the current limited quality of HMM (Hidden Markov Model) speech synthesis. This framework separates each of the effects of modelling to observe their independent effects on vocoded speech parameters in order to address the issues that are restricting the progression to highly intelligible and natural-sounding ...

In statistical HMM-based TTS systems (STTS), speech feature dynamics is modelled by firstand second-order feature frame differences, which, typically, do not satisfactorily represent frame to frame feature dynamics present in natural speech. The reduced dynamics results in over-smoothing of speech features, often sounding as muffled and buzzy synthesized speech. In this work we propose a method...

This special issue of the Journal consists of nearly two dozen articles that address both methodological approaches to Arabic Natural Language Processing and Automatic Speech Recognition as well as pilot-tested applications that are of commercial value. In keeping with prior special issues of this Journal, published under the auspices of the current Editor-in-Chief, this issue will consider bot...

This dissertation presents the importance of diphones’ duration and f0 information in generating more natural intonation in unit selection speech synthesis. The results showed that diphones’ duration or f0 information was highly correlated to one another due to the prosodic properties inherited from the recorded human speech. Also only raising the importance of duration and f0 information large...

With the deepening of the speech recognition research, improving the accuracy of the general recognition engine is becoming more and more difficult. For the noise problem of Chinese speech recognition, in this paper we made a brief review and analysis about the current related articles of the semantic similarity and the text-speech similarity. We compared the advantages and disadvantages of var...

We describe recent research to enhance a training system which interprets Call for Fire (CFF) radio artillery requests. The research explores the feasibility of extending the system to also understand calls for Close Air Support (CAS). This work includes automated analysis of complex language behavior in CAS missions, evaluation of speech recognition performance, and simulation of speech recogn...

Italian geminate consonants have been studied as for both their phonetic characteristics and their phonological status. As for the phonetic aspects, though, few works focus on kinematic data. This study relates on both acoustic and kinematic material, as well as on perception data, in order to get evidence on the phonological status of geminate consonants. A read speech corpus was collected and...