We present a new method for task-based speechto-speech machine translation evaluation, in which tasks are defined and assessed according to independent published standards, both for the military tasks performed and for the foreign language skill levels used. We analyze task success rates and automatic MT evaluation scores for 220 role-play dialogs. Each role-play team consisted of one native En...

A Pascal challenge entitled monaural multi-talker speech recognition was developed, targeting the problem of robust automatic speech recognition against speech like noises which significantly degrades the performance of automatic speech recognition systems. In this challenge, two competing speakers say a simple command simultaneously and the objective is to recognize speech of the target speake...

The present study aimed to identify strategies used to realize the speech act of offerin Persian. To do so, 195 male and female native Persian speakers were selected fromdiverse age ranges, educational backgrounds, and social classes, and were assigned a36-item Discourse Completion Task (DCT) to elicit the speech act of offer. Thirtyfield workers also recorded naturally occurring interactions c...

In view of the growing use of automatic speech recognition in the modern society, we study various alternative representations of the speech signal that have the potential to contribute to the improvement of the recognition performance. Specifically, the main targets of the present article are to overview and evaluate the practical importance of some recently proposed, and thus less studied, wa...

In this paper, we propose a novel method of normalizing the voice quality in an utterance for both clean speech and speech contaminated by noise. The normalization method is applied to the N-best hypotheses from an HMM-based classifier, then an SM (Sub-space Method)-based verifier tests the hypotheses after normalizing the monophone scores together with the HMMbased likelihood score. The HMM-SM...

This paper introduces the speech synthesis system developed by USTC for Blizzard Challenge 2014. Six Indian languages were evaluated this year, including Assamese, Gujarati, Hindi, Rajasthani, Tamil and Telugu. Two tasks were built for these languages: the mono-lingual task (IH1 hub task) and the multi-lingual task (IH2 spoken task). We submitted entries to both tasks in all languages. We submi...