Publishing Partner: Cambridge University Press CUP Extra Publisher Login
amazon logo
More Info


New from Oxford University Press!

ad

Speaking American: A History of English in the United States

By Richard W. Bailey

"Takes a novel approach to the history of American English by focusing on hotbeds of linguistic activity throughout American history."


New from Cambridge University Press!

ad

Language, Literacy, and Technology

By Richard Kern

"In this book, Richard Kern explores how technology matters to language and the ways in which we use it. Kern reveals how material, social and individual resources interact in the design of textual meaning, and how that interaction plays out across contexts of communication, different situations of technological mediation, and different moments in time."


Academic Paper


Title: Pronunciation Variation Modelling Using Accent Features
Paper URL: http://www.phon.ucl.ac.uk/home/mark/papers/eurosp2005tjalve.pdf
Author: Michael Tjalve
Email: click here TO access email
Institution: University College London
Author: Mark A Huckvale
Homepage: http://www.phon.ucl.ac.uk/home/mark/home.htm
Institution: University College London
Linguistic Field: Phonetics
Abstract: In this paper, we propose a novel method for modelling native accented speech. As an alternative to the notion of dialect, we work with the lower level phonological components of accents, which we term accent features. This provides us with a better understanding of how pronunciation varies and it allows us to give a much more detailed picture of a person’s speech./L//L/The accent features are included during phonological adaptation of a speaker-independent Automatic Speech Recognition system in an attempt to make it more robust when exposed to pronunciation variation thus improving recognition performance on accented speech./L//L/We employ a dynamic set-up in which the system first identifies the phonetic characteristics of the user’s speech. It then creates a model of the speaker’s phonological system and adapts the pronunciation dictionary to best match his/her speech. Recognition is subsequently carried out using the adapted pronunciation dictionary./L//L/Experiments on British English speech data show a significant relative improvement in error rate of 20% compared with the traditional non-adaptive method.
Type: Individual Paper
Status: Completed
Venue: Proc. EuroSpeech 2005, Lisbon, Portugal
URL: http://www.phon.ucl.ac.uk/home/mark/papers/eurosp2005tjalve.pdf


Add a new paper
Return to Academic Papers main page
Return to Directory of Linguists main page