| 書目名稱 | Phonological Parsing in Speech Recognition | | 編輯 | Kenneth W. Church | | 視頻video | http://file.papertrans.cn/747/746307/746307.mp4 | | 叢書名稱 | The Springer International Series in Engineering and Computer Science | | 圖書封面 |  | | 描述 | 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 ‘a(chǎn)bout‘ 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 r | | 出版日期 | Book 1987 | | 關(guān)鍵詞 | Allophon; Klang; Parsing; Phonem; cognition; phonetic transcription; speech recognition; transcription | | 版次 | 1 | | doi | https://doi.org/10.1007/978-1-4613-2013-5 | | isbn_softcover | 978-1-4612-9200-5 | | isbn_ebook | 978-1-4613-2013-5Series ISSN 0893-3405 | | issn_series | 0893-3405 | | copyright | Kluwer Academic Publishers 1987 |
The information of publication is updating
|
|
|Archiver|手機版|小黑屋|
派博傳思國際
( 京公網(wǎng)安備110108008328)
GMT+8, 2025-10-12 23:02
發(fā)表于 2025-3-21 17:17:01
