How Should a Speech Recognizer Work?
نویسندگان
چکیده
منابع مشابه
How Should a Speech Recognizer Work?
Although researchers studying human speech recognition (HSR) and automatic speech recognition (ASR) share a common interest in how information processing systems (human or machine) recognize spoken language, there is little communication between the two disciplines. We suggest that this lack of communication follows largely from the fact that research in these related fields has focused on the ...
متن کاملA Virtual Vocabulary Speech Recognizer
A system for the automatic recognition of human speech is described. A commercially available speech recognizer sees its recognition vocabulary increased through the use of virtual memory management techniques. Central to the design are issues concerning the nature of speech, its effectiveness as an isolated mode of communication with computers, and its role as a part of a multi-modal communica...
متن کاملHow to Grow A Recognizer
A recognizer is a computer program for locating objects of known classes within a complex signal. Best known examples include speech recognition and character recognition (OCR) systems, but an argument is made that the techniques apply in a broad spectrum of applications. This paper discusses the recognizer development process. Topics addressed include training sample collection, feature detect...
متن کاملStochastic k-Server: How Should Uber Work?
In this paper we study a stochastic variant of the celebrated k-server problem. In the kserver problem, we are required to minimize the total movement of k servers that are serving an online sequence of t requests in a metric. In the stochastic setting we are given t independent distributions 〈P1, P2, . . . , Pt〉 in advance, and at every time step i a request is drawn from Pi. Designing the opt...
متن کاملImproving Speech Recognizer Performance
This thesis investigates N-best hypotheses reranking techniques for improving speech recognition accuracy. We have focused on improving the accuracy of a speech recognizer used in a dialog system. Our post-processing approach uses a linear regression model to predict the error rate of each hypothesis from hypothesis features, and then outputs the one that has the lowest (recomputed) error rate....
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Cognitive Science
سال: 2005
ISSN: 0364-0213
DOI: 10.1207/s15516709cog0000_37