Speech Processing Tools

Organizer(s)

• Christoph Draxler, Institute of Phonetics and Speech Processing, Munich DE (draxler@phonetik.uni-muenchen.de)
• Toomas Altosaar, Aalto University School of Science and Technology, Helsinki University of Technology, SF (Toomas.Altosaar@hut.fi)
• Sadaoki Furui, Tokyo Institute of Technology, Tokyo, Japan (furui@cs.titech.ac.jp)
• Mark Liberman, Linguistic Data Consortium, Philadelphia

Synopsis

The proposed special session aims to establish a forum for developers of off-the shelf software for speech processing. Such a forum will improve the scientific visibility of tool development and allow developers to obtain academic recognition for their highly interdisciplinary work.

For Interspeech 2011, the focus of the special session should be on the interoperability of tools.

Description

The special session on Speech Processing Tools is about off-the-shelf software for speech technology - software that one can download or license which supports tasks relevant to the processing of speech data and which is intended to serve the linguist, phonetician, technologist or other researcher in his or her daily work. Examples of such software are SFS, Praat, ELAN, SpeechRecorder, Emu, Transcriber, NXT, etc. This session is not about clever algorithms (which are always useful and needed), but focuses much more on the joy of use, stability, appropriateness, availability, and interoperability.

The motivation for such a special session is that currently magnificent tools exist which are used in many labs. However, the people who developed these tools have problems getting proper recognition for their work (outside of the satisfaction of seeing one's own tools on other people's laptops during a conference).

In the scientific application area of software, tool development is considered less interesting than publishing results obtained with these tools. In computer science or software engineering, developing tools for a given application is considered "just application work" that only sometimes has to do with the frontiers of research.

Most speech technology or speech researchers will have had the experience that obtaining funding for tool development is next to impossible - one often has to hide development costs somewhere in the budget. With tool development receiving academic recognition this might slowly change for the better.

Submissions

The deadline for submitting a paper is 31 March 2011 at 23:59 GMT.

Submissions to the special event must adhere to the Interspeech Preparation Guidelines and will undergo the standard reviewing process.

Papers must be submitted via the Interspeech submission page.

When submitting a paper, you must choose only this special event in the field 'Special sessions, special events, or show & tell ONLY'.