Audiovisual interface for Czech spoken dialogue system

Matoušek

Hanzlíček

et al. 2020

IJCAI

This paper deals with expressive speech synthesis in a dialogue. Dialogue acts -discrete expressive categories -are used for expressivity description. The aim of the work is to create a procedure for development of expressive speech synthesis for a dialogue system in a limited domain. The domain is here limited to dialogues between a human and a computer on a given topic of reminiscing about personal photographs. To incorporate expressivity into synthetic speech, modifications of current algorithms used for neutral speech synthesis are made. An expressive speech corpus is recorded, annotated using a predefined set of dialogue acts, and its acoustic analysis is performed. Unit selection and HMM-based methods are used to synthesize expressive speech, and an evaluation using listening tests is presented. The listeners asses two basic aspects of synthetic expressive speech for isolated utterances: speech quality and expressivity perception. The evaluation is also performed for utterances in a dialogue to asses appropriateness of synthetic expressive speech. It can be concluded that synthetic expressive speech is rated positively even though it is of worse quality when comparing with the neutral speech synthesis. However, synthetic expressive speech is able to transmit expressivity to listeners and to improve the naturalness of the synthetic speech.Povzetek: Razvita je metoda za izrazno govorno sintezo včeščini.

Section: Introductionmentioning

confidence: 99%

Dialogue act based expressive speech synthesis in limited domain for the Czech language

Matoušek

Hanzlíček

et al. 2020

IJCAI

“…In our work, we restricted the domain to conversations between seniors and a computer. As the topic for these discussions, personal photographs were chosen since the work started as a part of a major project whose aim was to develop a virtual senior companion with an audiovisual interface [1]. The more detailed background is described in [2] or [3].…”

Section: Introductionmentioning

confidence: 99%

Enumerating differences between various communicative functions for purposes of Czech expressive speech synthesis in limited domain

2012

Interspeech 2012

This paper deals with determination of a penalty matrix that should represent differences between various communicative functions. These are supposed to describe expressivity that can occur in expressive speech and were designed to fit a limited domain of conversations between seniors and a computer on a given topic. The penalty matrix is assumed to increase a rate of the expressivity perception in synthetic speech produced by unit selection method. It should reflect both acoustic differences and differences based on human perception of expressivity.

“…As the topic for these discussions, personal photographs were chosen since the work started as a part of a major project whose aim was to develop a virtual senior companion with an audiovisual interface [7] (the more detailed background is described in [8][9][10]). Such a companion should help the elderly people when they are alone and want to talk to someone.…”

Section: Introductionmentioning

confidence: 99%

Improvements in Czech Expressive Speech Synthesis in Limited Domain

Matoušek

2013

Speech and Computer

Abstract. In our recent work, a method on how to enumerate differences between various expressive categories (communicative functions) has been proposed. To improve the overall impact of this approach to both the quality of synthetic expressive speech and expressivity perception by listeners, a few modifications are suggested in this paper. The main ones consist in a different way of expressive data processing and penalty matrix calculation. A complex evaluation using listening tests and some auxiliary measures was performed.