Automated Discovery of Direct Speech to Increase Quality and Battery Saving in Telephony

In a common talk over mobile phone there may be references to the speeches of the third persons or the indirect references to the previous words pronounced by the present partner. However, for the automatic control of telephone talks and their quality, that we started in one of our previous paper, it is extremely important to know whether some phrase was pronounced in the direct speech format, or as an indirect spoken phrase construction. The research provided in the present paper, applied an acoustic technique analysis scheme to study the role of pauses. It led us to the conclusion that the sufficient value of the timing pause in front of the phrase may be the key allowing to distinguish the direct oral speech from the indirect one. The examples, confirming this conclusion and its role in the power control, that we proposed half a century ago, are provided in this paper. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Авторы
Stefanuk V.L. , Savinitch L.V.
Сборник материалов конференции
Издательство
Springer Science and Business Media Deutschland GmbH
Язык
Английский
Страницы
169-178
Статус
Опубликовано
Том
777 LNNS
Год
2023
Организации
  • 1 Institute for Information Transmission Problems of Russian Academy of Sciences, Moscow, Russian Federation
  • 2 Peoples’ Friendship University of Russia, Moscow, Russian Federation
Ключевые слова
Collective of radio stations; Data base; Direct speech; Indirect speech; Pause; Power control; Prosodic element; Sounding speech; Tensor calculus
Цитировать
Поделиться

Другие записи