Change search
ReferencesLink to record
Permanent link

Direct link
An Information Theoretic Approach to Predict Speech Intelligibility for Listeners with Normal and Impaired Hearing
KTH, School of Electrical Engineering (EES), Sound and Image Processing.
KTH, School of Electrical Engineering (EES), Sound and Image Processing.
2007 (English)In: INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, BAIXAS, FRANCE: ISCA-INST SPEECH COMMUNICATION ASSOC , 2007, 1345-1348 p.Conference paper (Refereed)
Abstract [en]

A computational method to predict speech intelligibility in noisy environments has been developed. By modeling speech and noise as stochastic signals, the information transmission through a given auditory model can be estimated. Rate-distortion theory is then applied to predict speech recognition performance. Results are compared with subjective tests on normal and hearing impaired listeners. It is found that the method underestimates the supra-threshold deficits of hearing impairment, which is believed to be due to an overly simple auditory model and a small dictionary size.

Place, publisher, year, edition, pages
BAIXAS, FRANCE: ISCA-INST SPEECH COMMUNICATION ASSOC , 2007. 1345-1348 p.
Keyword [en]
speech intelligibility, speech perception, auditory models
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:kth:diva-25766ISI: 000269998600337ScopusID: 2-s2.0-56149113289ISBN: 978-160560316-2OAI: oai:DiVA.org:kth-25766DiVA: diva2:359741
Conference
Interspeech Conference 2007, Antwerp, BELGIUM, AUG 27-31, 2007
Available from: 2010-10-29 Created: 2010-10-29 Last updated: 2011-09-13Bibliographically approved
In thesis
1. Probabilistic Modelling of Hearing: Speech Recognition and Optimal Audiometry
Open this publication in new window or tab >>Probabilistic Modelling of Hearing: Speech Recognition and Optimal Audiometry
2009 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

Hearing loss afflicts as many as 10\% of our population.Fortunately, technologies designed to alleviate the effects ofhearing loss are improving rapidly, including cochlear implantsand the increasing computing power of digital hearing aids. Thisthesis focuses on theoretically sound methods for improvinghearing aid technology. The main contributions are documented inthree research articles, which treat two separate topics:modelling of human speech recognition (Papers A and B) andoptimization of diagnostic methods for hearing loss (Paper C).Papers A and B present a hidden Markov model-based framework forsimulating speech recognition in noisy conditions using auditorymodels and signal detection theory. In Paper A, a model of normaland impaired hearing is employed, in which a subject's pure-tonehearing thresholds are used to adapt the model to the individual.In Paper B, the framework is modified to simulate hearing with acochlear implant (CI). Two models of hearing with CI arepresented: a simple, functional model and a biologically inspiredmodel. The models are adapted to the individual CI user bysimulating a spectral discrimination test. The framework canestimate speech recognition ability for a given hearing impairmentor cochlear implant user. This estimate could potentially be usedto optimize hearing aid settings.Paper C presents a novel method for sequentially choosing thesound level and frequency for pure-tone audiometry. A Gaussianmixture model (GMM) is used to represent the probabilitydistribution of hearing thresholds at 8 frequencies. The GMM isfitted to over 100,000 hearing thresholds from a clinicaldatabase. After each response, the GMM is updated using Bayesianinference. The sound level and frequency are chosen so as tomaximize a predefined objective function, such as the entropy ofthe probability distribution. It is found through simulation thatan average of 48 tone presentations are needed to achieve the sameaccuracy as the standard method, which requires an average of 135presentations.

Place, publisher, year, edition, pages
Stockholm: KTH, 2009. ix, 35 p.
Series
Trita-EE, ISSN 1653-5146 ; 2009:023
Keyword
auditory models, probabilistic modelling, speech modelling, human speech recognition, hearing aids, cochlear implants, psychoacoustics, diagnostic methods, optimal experiments, audiometry
Identifiers
urn:nbn:se:kth:diva-10386 (URN)978-91-7415-310-1 (ISBN)
Presentation
2009-05-20, E2, Lindstedtsvägen 3, 11428 Stockholm, 13:00 (English)
Opponent
Supervisors
Available from: 2009-05-14 Created: 2009-05-08 Last updated: 2010-10-29Bibliographically approved

Open Access in DiVA

No full text

Scopus

Search in DiVA

By author/editor
Stadler, SvanteLeijon, Arne
By organisation
Sound and Image Processing
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar

Total: 54 hits
ReferencesLink to record
Permanent link

Direct link