Summary of the paper
| Title | LIPS: A Tool for Predicting the Lexical Isolation Point of a Word |
|---|---|
| Authors | Andrew Thwaites, Jeroen Geertzen, William D. Marslen-Wilson and Paula Buttery |
| Abstract | We present LIPS (Lexical Isolation Point Software), a tool for accurate lexicalisolation point (IP) prediction in recordings of speech. The IP is the point intime in which a word is correctly recognised given the acoustic evidenceavailable to the hearer. The ability to accurately determine lexical IPs is ofimportance to work in the field of cognitive processing, since it enables theevaluation of competing models of word recognition. IPs are also of importancein the field of neurolinguistics, where the analyses ofhigh-temporal-resolutionneuroimaging data require a precise time alignment of the observed brainactivity with the linguistic input. LIPS provides an attractive alternative tocostly multi-participant perception experiments by automatically computing IPsfor arbitrary words. On a test set of words, the LIPS system predicts IPs witha mean difference from the actual IP of within 1ms. The difference from thepredicted and actual IP approximate to a normal distribution with a standarddeviation of around 80ms (depending on the model used). |
| Language | Language modelling |
| Topics | Tools, systems, applications, Cognitive methods, Language modelling |
Full paper  |
LIPS: A Tool for Predicting the Lexical Isolation Point of a Word |
| Bibtex | @InProceedings{THWAITES10.326, author = {Andrew Thwaites, Jeroen Geertzen, William D. Marslen-Wilson and Paula Buttery}, title = {LIPS: A Tool for Predicting the Lexical Isolation Point of a Word}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |