First International Conference on Spoken Language Processing (ICSLP 90)

Kobe, Japan
November 18-22, 1990

Spoken Language in Interpreted Telephone Dialogues

Sharon L. Oviatt, Philip R. Cohen, Ann M. Podlozny

Artificial Intelligence Center, SRI International, Menlo Park, California, USA

This research outlines the predominant dialogue and performance characteristics of 3-person interpreted telephone speech during service-oriented dialogues, in comparison with those of 2-person noninterpreted dialogues. An empirical study was conducted in which 12 native English speakers each made one telephone call through an experienced telephone interpreter to a Japanese confederate who did not speak English, and a second call to a Japanese confederate fluent in English. In total, 24 dialogues were collected, each one containing two successfully completed service tasks, or 48 tasks total. This paper reports on comparisons performed between 3-person interpreted and 2-person noninterpreted speech, based on the same pool of tasks and English subjects. The unique characteristics of interpreted telephone dialogues are outlined, including structural and referential features, miscommunications and other performance characteristics, confirmatory language, and linguistic indirection. In addition, a.n analysis is presented of interpreters' strategic management of turn shifts and of the content and sequencing of information passed among speakers. The long-term goal of this exploratory research is the modelling of human speech, and the specification of preliminary target requirements for future automatic systems.

Full Paper

Bibliographic reference.  Oviatt, Sharon L. / Cohen, Philip R. / Podlozny, Ann M. (1990): "Spoken language in interpreted telephone dialogues", In ICSLP-1990, 1305-1308.