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.
Two large datasets have been made available for the session,
Any work that applies a microscopic view will be considered relevant to the special session. Particular topics include, but are not limited to,
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).
If you have any questions regarding the session please don't hesitate to contact one of the organizers listed below,