Session I: Evaluating Spoken Language
نویسنده
چکیده
The existing methods for evaluation evolved from the techniques used for the speech recognition systems. In tasks such as resource management, there is a closed vocabulary and the data is read speech. The main evaluation criteria is recognition accuracy, i.e., how many words in the test set are recognized correctly. To perform this evaluation, the researchers need a large database of read speech. Such data is relatively inexpensive to obtain in sufficient quantities.
منابع مشابه
Summary of Session 2: Spoken Language Systems I
This session included descriptions of Spoken Language Systems under development at BBN Systems and Technologies, Carnegie Mellon University, Massachusetts Institute of Technology and Unisys. The topics covered a variety of issues including semantic interpretation (BBN), modeling "noise words" for spontaneous (vs. read) speech (CMU), dialogue management (Unisys) and systems issues (MIT and Unisys).
متن کاملOn the Use of Diary Study to Investigate Avoidance Strategy in Spoken English Courses
In the present study, an attempt is made to investigate the frequency and motives of using avoidance strategies by a group of Iranian intermediate language learners through their own journal writing. The effect of gender on the use of avoidance strategies is to be investigated as well. Thirty nine female and twenty three male learners enrolled in an English language spoken course in a private E...
متن کاملSession 1: Spoken Language Systems
Without the ability to interpret natural language, speech recognition is suited only for a subset of tasks (though certainly not trivial ones), such as data entry, simple commands or dictation. Similarly, without speech recognition natural language is restricted to the interpretation of written language, a stylized form of human communication. Spoken language systems thus represent an attempt t...
متن کاملSpoken Language Systems II
The papers in this session were concerned with higher-level processing in speech recognition systems and, in some cases, the interface between the speech-recognition and natural-language components of a spoken language system. The session consisted of talks from four DARPA sites, Dragon Systems, SRI International, BBN Systems and Technologies, and MIT Lincoln Laboratory. These talks were follow...
متن کاملSpoken language variation over time and state in a natural spoken dialog system
We are interested in adaptive spoken dialog systems for automated services. Peoples’ spoken language usage varies over time for a fixed task, and furthermore varies depending on the state of the dialog. We will characterize and quantify this variation based on a database of 20K user-transactions with AT&T’s experimental ‘How May I Help You?’ spoken dialog system. We then report on a language ad...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1992