Phonological Parsing in Speech Recognition.pdf

Phonological Parsing in Speech Recognition PDF

K. Church

It is well-known that phonemes have different acoustic realizations depending on the context. Thus, for example, the phoneme /t! is typically realized with a heavily aspirated strong burst at the beginning of a syllable as in the word Tom, but without a burst at the end of a syllable in a word like cat. Variation such as this is often considered to be problematic for speech recogni­ tion: (1) In most systems for sentence recognition, such modifications must be viewed as a kind of noise that makes it more difficult to hypothesize lexical candidates given an in­ put phonetic transcription. To see that this must be the case, we note that each phonological rule [in a certain example] results in irreversible ambiguity-the phonological rule does not have a unique inverse that could be used to recover the underlying phonemic representation for a lexical item. For example, . . . schwa vowels could be the first vowel in a word like about or the surface realization of almost any English vowel appearing in a sufficiently destressed word. The tongue flap [(] could have come from a /t! or a /d/. [65, pp. 548-549] This view of allophonic variation is representative of much of the speech recognition literature, especially during the late 1970s. One can find similar statements by Cole and Jakimik [22] and by Jelinek [50].

Buy the Paperback Book Phonological Parsing In Speech Recognition by K. Church at Indigo.ca, Canada's largest bookstore. Free shipping and pickup in store on eligible orders.

6.61 MB DATEIGRÖSSE
146129200X ISBN
Englisch SPRACHE
Phonological Parsing in Speech Recognition.pdf

Technik

PC und Mac

Lesen Sie das eBook direkt nach dem Herunterladen über "Jetzt lesen" im Browser, oder mit der kostenlosen Lesesoftware Adobe Digital Editions.

iOS & Android

Für Tablets und Smartphones: Unsere Gratis tolino Lese-App

Andere eBook Reader

Laden Sie das eBook direkt auf dem Reader im Hugendubel.de-Shop herunter oder übertragen Sie es mit der kostenlosen Software Sony READER FOR PC/Mac oder Adobe Digital Editions.

Reader

Öffnen Sie das eBook nach der automatischen Synchronisation auf dem Reader oder übertragen Sie es manuell auf Ihr tolino Gerät mit der kostenlosen Software Adobe Digital Editions.

Aktuelle Bewertungen

avatar
Sofia Voigt

plications in speech synthesis, recognition and understanding. ... 2-1 Lexical representation for the word \monkey" | shown here in a parse tree format. Decades of linguistic and phonetic study precedes speech recognition. ... we use sliding windows of width 25ms and 10ms apart to parse the audio waveform.

avatar
Matteo Müller

Review of "Phonological parsing in speech …

avatar
Noel Schulze

Oct 16, 2017 ... On the base of a recent work on speech processing computations ... a crucial role in parsing speech units in the acoustic signal (Buiatti et al.

avatar
Jason Lehmann

Phonological Parsing In Speech Recognition, …

avatar
Jessica Kohmann

Get this from a library! Phonological parsing in speech recognition. [Kenneth Ward Church]