[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

call for papers, IFSA-SCIS special session 'big speech data analysis'



I am organizing (with Paul De Palma) a special session on big data and speech at a great "soft computing and intelligent systems" meeting June 27-30, 2017.  The meeting is in Otsu, Japan--but accepted papers can be delivered remotely (e.g., Skype).  Details below.

The deadline to submit an abstract is Jan. 15.  The process is to submit an abstract here, and during the submission process you identify the special session below.  I'm happy to answer any questions (mark.vandam@xxxxxxx).

This is a broad call for papers (from students, too) looking at how big data bear on questions of speech and language.  Papers can be empirical or theoretical.

The meeting is the Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing andIntelligent Systems (IFSA-SCIS 2017), Otsu, Japan, 27th-30th June 2017.  This is an IEEE group.  Here is the meeting description.


Special Session:
"Fuzzy processing of very large speech language databases" This session will look at automatic processing of naturalistic speech in very large databases (VLDB). Recent attempts such as the HomeBank project (http://homebank.talkbank.org) exist in part to make publicly available a very large database of naturally collected, acoustic speech and language samples from a wide variety of real-life language use environments. The data constitute many tens-ofthousands of hours of acoustic recordings, results of automated processing including automatic speech and talker recognition and diarization, and associated meta-data such as language characteristics, demographics of participants, socio-economic status, and many other variables. The data has been used to explore typical and disordered (e.g., deafness, autism) language development, improvements to and assessment of automatic processing approaches, database management techniques, and hardware technology, among others. The papers in this session will explore a number of empirical and theoretical issues in this domain.
Session organizers: Paul De Palma (Gonzagu U), Mark VanDam (Wash St U)

-----
Mark VanDam
Dept. Speech & Hearing Sciences
Elson S. Floyd College of Medicine
Washington State University
mark.vandam@xxxxxxx
https://labs.wsu.edu/vandam