Models of Human Phone Transcription in Noise Based on Intelligibility Predictors

The key findings of the experiments are the following: (1) the Articulation Index model recognition accuracy works very well in some phonetic contexts and fails in others, (2) the Articulation Index model is the average of a number of more specific models with their own parameters, (3) audibility of speech does not explain all variation but explains a great deal of it, and (4) phonetic importance is not spread uniformly over the time and frequency. We speculate that humans may use different representations of speech, depending on the phonetic context, and we suggest experiments controlling frequency-band specific signal-to-noise ratio and level to resolve these issues.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Electrical and Computer Engineering

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2015

Author dc:creator

• Lobdell, Bryce E.

Contributors dc:contributor

• Hasegawa-Johnson, Mark A.

• Speech Communication

Language dc:language

eng

Identifier

(MiAaPQ)AAI3363022

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/81127