ERIC Number: ED043866
Record Type: Non-Journal
Publication Date: 1970-Nov
Reference Count: N/A
The Mechanical Recognition of Speech: Prospects for Use in the Teaching of Languages.
Bulletin of the ERIC Clearinghouse for Linguistics, n18 p1-7 Nov 70
This paper begins with a brief account of the development of automatic speech recogniton (ASR) and then proceeds to an examination of ASR systems typical of the kind now in operation. It is stressed that such systems, although highly developed, do not recognize speech in the same sense as the human being does, and that they can not deal with a continuous random stream of speech but rather with segments of the length of a short sentence, selected from among up to a hundred possible choices. The use of ASR in educational technology is seen as inevitable since it will make it possible for a teaching machine to recognize and evaluate a student's spoken response, and the importance of this development in vitalizing present educational technology is discussed at some length. Finally a hierarchy of achievable strategies for the use of ASR in teaching are examined, ranging from simple to sophisticated. Discussed are: sound/no sound discrimination, gross evaluation of utterance, gross approximation of choice, determination of acceptable pronunciation, diagnostic evaluation of pronunciation, and multiple choice drills. The author believes that teachers should welcome developments in ASR and help to participate in the development of education technology for language teaching. (FWB)
Publication Type: N/A
Education Level: N/A
Authoring Institution: Center for Applied Linguistics, Washington, DC. ERIC Clearinghouse for Languages and Linguistics.