Edinburgh Research Explorer

Detection of Phonological Features in Continuous Speech using Neural Networks

Research output: Contribution to journalArticle

Related Edinburgh Organisations

Open Access permissions

Open

Documents

Original languageEnglish
Pages (from-to)333-353
Number of pages21
JournalComputer Speech and Language
Volume14
Issue number4
DOIs
Publication statusPublished - 2000

Abstract

We report work on the first component of a two stage speech recognition architecture based on phonological features rather than phones. The paper reports experiments on three phonological feature systems: 1) the Sound Pattern of English (SPE) system which uses binary features, 2)a multi valued (MV) feature system which uses traditional phonetic categories such as manner, place etc, and 3) Government Phonology (GP) which uses a set of structured primes. All experiments used recurrent neural networks to perform feature detection. In these networks the input layer is a standard framewise cepstral representation, and the output layer represents the values of the features. The system effectively produces a representation of the most likely phonological features for each input frame. All experiments were carried out on the TIMIT speaker independent database. The networks performed well in all cases, with the average accuracy for a single feature ranging from 86 to 93 percent. We describe these experiments in detail, and discuss the justification and potential advantages of using phonological features rather than phones for the basis of speech recognition.

Download statistics

No data available

ID: 2077746