Title :
Recent advances in speech recognition
Author_Institution :
Efrat FutureTechnol. Ltd., Tel Aviv, Israel
Abstract :
Summary form only given. Speech recognition systems tend to consist of the following modules: input (acquisition and acoustic processing); classification (phoneme/word recognition); language (lexical/syntactic/semantic) processing; output (actions to be performed); although in many systems these modules are further subdivided, in some systems some of these modules may be omitted or several may be combined.
Keywords :
speech recognition; acoustic processing; acquisition; classification; language processing; lexicography; modules; phoneme recognition; semantics; speech recognition; syntax; word recognition; Artificial neural networks; Auditory system; Feature extraction; Hidden Markov models; Natural languages; Neurophysiology; Psychology; Speech recognition; Text recognition; Viterbi algorithm;
Conference_Titel :
Electrical and Electronics Engineers in Israel, 1995., Eighteenth Convention of
Conference_Location :
Tel Aviv, Israel
Print_ISBN :
0-7803-2498-6
DOI :
10.1109/EEIS.1995.513819
