Motivation

Existing models of intelligibility can successfully estimate word identification in broadly stated noise conditions. These predictions may be characterized as macroscopic in that they represent averages - averages over many listeners and over many speech tokens. This Special Session asks whether we can go beyond macroscopic predictions. We invite work that might contribute to a new breed of microscopic models that are evaluated according to their ability to make precise predictions of what a specific listener might hear in response to a specific noisy speech token. Developing such models will deepen our understanding of speech perception and enable a wealth of new intelligibility modeling applications. To focus the session, we have provided contributers with access to two large corpora that record "slips of the ear" made by listeners hearing words in complex noise backgrounds. Participants are encouraged to use this data where it can support the aims of their work.

Data

Two large datasets have been made available for the session,

• English Consistent Confusion Corpus
• Spanish Consistent Confusions Corpus

Topics

Any work that applies a microscopic view will be considered relevant to the special session. Particular topics include, but are not limited to,

• Psycholinguistic analysis of misperceptions
• Statistical speech modelling for intelligibility prediction
• Analysis and understanding of misperceptions in noise
• Modelling the effects of speaker and speaking-style variation
• Intelligibility and non-native talkers and/or listeners
• Model-driven speech intelligibility enhancement
• Microscopic models of binaural intelligibility in noise
• New methodologies for intelligibility model evaluation
• Speech resources for intelligibility model evaluation
• Understanding speech perception through ``big data’’ and crowd-sourcing

Important Dates

• Submission: March 23, 2016
• Acceptance notification: June 10, 2016
• Camera-ready paper: June 24, 2016
• Conference dates: September 8-10, 2016

Paper Submission

Papers for this special session have to be submitted following the same schedule and procedure as regular Interspeech papers; the papers will undergo the same review process by anonymous and independent reviewers.

Please submit your paper to the special session "Intelligibility under the microscope" (in area 1: Speech Perception, Production and Acquisition).

Organizers

If you have any questions regarding the session please don't hesitate to contact one of the organizers listed below,

• Ricard Marxer, University of Sheffield, UK
• Jon Barker, University of Sheffield, UK
• Martin Cooke, Ikerbasque, Spain