Many studies have been reported in the domain of speech-to-speech machine translation systems for travel conversation use. Therefore, a large number of travel domain corpora have become available in recent years. From a wider viewpoint, speech-to-speech systems are required for many purposes other than travel conversation. One of these is monologues (e.g., TV news, lectures, technical presentat...

The present paper presents a unified analysis of free and embedded indirect speech, with a specific focus on German. First we need a context-based analysis of indexicals (rigid/shiftable) which can capture their orientation in uses in indirect speech. The analysis includes a treatment of the German reportative subjunctive as a shiftable indexical tense. Indirect speech in embedded clauses of th...

Previous analyses on friendly speech were made using dialogues without differentiating their linguistic functions. This paper reports an analysis on declarative and interrogative sentences respectively. Pitch and duration of prosodic words were statistically analyzed and compared concerning factors of their positions and stresses. Based on the acoustic investigation of friendly speech, tonal pi...

Spontaneous conversational speech has many characteristics that are currently not well modelled in unit selection and HMM-based speech synthesis. But in order to build synthetic voices more suitable for interaction we need data that exhibits more conversational characteristics than the generally used read aloud sentences. In this paper we will show how carefully selected utterances from a spont...

This paper describes a technique for synthesizing speech with an arbitrary speaker characteristics using speaker independent speech units, which we call “average voice” units. The technique is based on an HMM-based text-to-speech (TTS) system and MLLR adaptation algorithm. In the HMM-based TTS system, speech synthesis units are modeled by multi-space probability distribution (MSD) HMMs which ca...

Why is ordinary language vague? We argue that in contexts which a cooperative speaker not perfectly informed about the world, use of vague expressions can offer an optimal tradeoff between truthfulness (Gricean Quality) and informativeness Quantity). Focusing on approximation such as “around”, are semantically vague, we show they allow to convey indirect probabilistic information, way give list...

A grammar checker is a tool to check each sentence in text see whether it conforms the grammar. In case finds structure that conflicts with conformity grammar, would give suggestions for alternatives. The checkers European languages and some Indic are well developed. However, perhaps, owing Tamil being morphologically rich agglutinative language this has been challenging task. An approach detec...