CONTENTS

Speech Synthesizers have traditionally been built on carefully read speech that is recorded in studio environment. Such voices are suboptimal for use in noisy conditions, which is inevitable in a majority of deployed speech systems. In this work, we attempt to modify the output of the speech synthesizers to make it more appropriate for noisy environments. Comparison of spectral and prosodic fea...

During interpersonal conversation, both children and adults adapt the basic acoustic-prosodic features of their speech to converge with those of their conversational partner. In this study, 7-to-10year-old children interacted with a conversational interface in which animated characters used text-to-speech output (TTS) to answer questions about marine biology. Analysis of children’s speech to di...

This paper introduces a new concept in speech synthesisers by constructing devices and methods by which they can be operated in real-time. Further development of this concept may lead to an improvement in the conversational capabilities of people with ‘speech communicators’. This paper outlines the current limitations of such systems and then describes the methods used to give the user real-tim...

It is tempting for those in the field of organic synthesis to liken the process of retrosynthesis to a game of chess. That the world chess champion was recently defeated by a computer leads us to think that perhaps new and powerful computing methods could be applied to synthetic problems. Here the analogy between synthesis and chess is outlined. Achievements in the 35-year history of computer-a...

This study investigates F0 declination as a global-level prosodic phenomenon, establishing a new discourse-based model of prosodic structure in Japanese. The model includes two levels of declination in a hierarchical order: utterance units and prosodic paragraphs, a higher level of declination consisting of embedded declinations. Comparing and contrasting three types of discourse -read speech, ...

This paper describes the Bell Labs Russian text-to-speech system, a concatenative system with extensive text-analysis capabilities. The construction of Russian-specific modules will be discussed, including the text-analysis module, the acoustic inventory, the duration module, and the intonation module.

It was previously observed [1] that the order of presentation of paired stimuli influenced the number of different responses in same-different tasks in speech synthesis evaluation. This paper investigates this phenomenon within the context of cognitive psychology and demonstrates that, as the cognitive psychology literature suggests, there is an effect relating to the prototypicality of the sti...