- From: Djoerd Hiemstra <sigir07@cs.utwente.nl>
- Date: Wed, 16 May 2007 15:43:04 +0200
- To: public-sws-ig@w3.org
******************************************************* 2nd Call for papers: Deadline extension to 28 May 2007 Searching Spontaneous Conversational Speech ACM SIGIR 2007 Workshop - 27 July 2007 http://hmi.ewi.utwente.nl/sscs ******************************************************* Background Nearly a decade ago, we learned from the TREC Spoken Document Retrieval (SDR) track that searching speech was a "solved problem." Three factors were key to this success: (1) broadcast news has a "story" structure that resembled written documents, (2) the redundancy present in human language meant that search effectiveness held up well over a reasonable range of transcription accuracy, and (3) sufficiently accurate Large-Vocabulary Continuous Speech Recognition (LVCSR) systems could be built for the planned speech of news announcers. The long-term trend in speech recognition research has been toward transcription of progressively more challenging sources. Over the last few years, LVCSR for spontaneous conversational speech has improved to a degree where transcription accuracy comparable to what was previously found to be effective for broadcast news can now be achieved for a diverse range of sources. This has inspired a renaissance in research on search and browse technology for spoken word collections in communities focused on: (1) archived cultural heritage materials (e.g., interviews and parliamentary debates), (2) discussion venues (e.g., business meetings and classroom instruction), and (3) broadcast conversations (e.g., in-studio talk shows and call-in programs). Test collections are being developed in individual projects around the world, and some comparative evaluation activity for speech search technology has developed over this period. The time seems now right to look more broadly across these research communities for potential synergies that can help to shape the information retrieval research agenda of each of these communities by sharing ideas and resources. Context This workshop is part of ACM SIGIR 2007, 23-27 July, Amsterdam, The Netherlands (http://www.sigir2007.org/). Workshop Organization Franciska de Jong, University of Twente, The Netherlands Douglas Oard, University of Maryland, USA Roeland Ordelman, University of Twente, The Netherlands Stephan Raaijmakers, TNO ICT, The Netherlands Format We plan to organize the workshop as a mix of oral presentations, panel discussions and a poster session. Workshop Proceedings will be available at the workshop. Possibilities for a special journal issue with a selection of workshop contributions are under negotiation. Workshop Topics We welcome contributions on a range of cross-cutting issues, including: * Segmentation (e.g., speaker turns, topic shifts) * Content characterization (e.g., LVCSR, word lattice search, spoken term detection on phone lattice) * Classification (e.g., speaker, topic, decision, non-speech acoustic event) * Exploiting multimodality (integrating features from associated non-speech content) * Search effectiveness (e.g., evidence combination, expansion) * Interaction design (e.g., query formulation, result presentation, search strategies) * Evaluation (content sources, measures, test collection design, user study design) * Broader issues (applications, intellectual property, privacy) Submission Types Two types of submissions are invited: research papers for oral or poster presentation, and position papers for the selection of discussants and panelists. Submission Guidelines Information on how to submit can be found in the submission guidelines (http://hmi.ewi.utwente.nl/sscs/submissions). Important Dates Call for papers: April 18, 2007 Papers due: May 28, 2007 Acceptance notification: June 13, 2007 Final versions due: July 1, 2007 Program Committee Samy Bengio (Google) Laurence Devillers (LIMSI) Sadaoki Furui (TITECH) Marcello Federico (FBK-IRST) Jon Fiscus (NIST) John Garofolo (NIST) Sam Gustman (USC) Thomas Hain (Sheffield) John Hansen (UT Dallas) Alex Hauptmann (CMU) Julia Hirschberg (Columbia) Diana Inkpen (Ottawa) Gareth Jones (DCU) David van Leeuwen (TNO) Lori Lamel (LIMSI) Christian Mueller (ICSI) Steve Renals (Edinburgh) Salim Roukos (IBM Research) Liz Shriberg (SRI and ICSI)
Received on Wednesday, 16 May 2007 13:43:10 UTC