Book ChapterDOI
Self-Organized Continuous Speech Recognition
Frederick Jelinek
- pp 231-238
Reads0
Chats0
TLDR
Current efforts to recognize continuous (or “connected”) speech are aimed at constructing a voice-excited “typewriter” that automatically transcribes natural speech into ordinary (e.g. English) written form.Abstract:
Current efforts to recognize continuous (or “connected”) speech are aimed at constructing a voice-excited “typewriter” that automatically transcribes natural speech into ordinary (e.g. English) written form. So far, however, only very restricted speech has been recognized. The sentences that are spoken must either be prescribed a priori by an artificial grammar which the experimenter has designed, or else limited by a vocabulary and a restricted area of discourse such as that used in business letters, book reviews, or airline reservation systems. These latter so-called natural tasks are generally much more difficult than the artificial ones (given a fixed vocabulary).read more
Citations
More filters
Book ChapterDOI
Continuous automatic speech recognition by lipreading
TL;DR: While this study focuses on the feasibility, validity, and segregated contribution of exclusively continuous OASR, future highly robust recognition systems should combine optical and acoustic information with syntactic, semantic and pragmatic aids.
An acoustic-phonetic approach to speech recognition : application to the semivowels
TL;DR: Originally presented as author's thesis (Ph. D.-- Massachusetts Institute of Technology), 1987.
Book ChapterDOI
Acoustic-Phonetic Decoding and Adaptation in Continuous Speech Recognition
TL;DR: The novelty of this phonetic recognizer mainly lies in the strategy of recognition that takes into account different levels of recognition, the way by which segmentation and identification are combined, and the adaptation module which gives the phonetic processor leave to easily adapt to new speakers or to new tasks.
Journal ArticleDOI
A Voice Input System for Automobiles Using a Microprocessor
TL;DR: A microprocessor-based voice input system for automobiles has been developed by Nissan and a special car equipped with the voice input System was exhibited at the 1981 Tokyo Motor Show.
Confidence and Rejection in Automatic Speech Processing
TL;DR: Confidence and Rejection in Automatic Speech Recognition: Trust, confidence, and rejection in automatic speech recognition studies are compared.
References
More filters
Book
Introduction to Theoretical Linguistics
TL;DR: 1. Linguistics: the scientific study of language 2. The structure of language 3. The sounds of language 4. Grammar: general principles 5. Grammatical units 6. grammatical structure 7. Semantic structure Notes and references
Journal ArticleDOI
Continuous speech recognition by statistical methods
TL;DR: Experimental results are presented that indicate the power of the methods and concern modeling of a speaker and of an acoustic processor, extraction of the models' statistical parameters and hypothesis search procedures and likelihood computations of linguistic decoding.