This page gathers information about diverse workshops that were (or will be) held on Automatic Meeting Recognition.

ICASSP 2004 Meeting Recognition Workshop (May 17, 2004) sponsored by NIST.

Introduction

Huge efforts are being expended in mining information in newswire, news broadcasts, and conversational speech and in developing interfaces to metadata extracted in these domains. However, until recently, relatively little has been done to address such applications in the more challenging and equally important meeting domain.

The development of smart meeting room core technologies that can automatically recognize and extract important information from multi-media sensor inputs will provide an invaluable resource for a variety of business, academic, and governmental applications. Such metadata will provide the basis for the development of second-tier meeting applications that can automatically process, categorize, and index meetings. Third-tier applications will provide a context-aware collaborative interface between live meeting participants, remote participants, meeting archives and vast online resources.

The meeting domain has several important properties not found in other domains and which are not currently being focused on in other research programs: multiple forums and vocabularies, highly-interactive/simultaneous speech, multiple distant microphones, multiple camera views, and multi-media/multi-modal information integration.

The Rich Transcription 2004 Spring Meeting Recognition Workshop at ICASSP 2004 on May 17 in Montreal brought together the community of researchers working in this new and challenging domain to discuss the challenges, the current state-of-the-art, and future plans and collaborations. Discussions included the results of the March 2004 Rich Transcription Meeting Recognition Evaluation including both Speech-to-Text Transcription and Speaker Segmentation technologies, related research work in the meeting domain, related governmental programs, and future collaborations.

Evaluation

The RT-04 Spring Recognition Evaluation was part of the NIST Rich Transcription Evaluation series and included both speaker segmentation and speech-to-text transcription tasks in the meeting domain. The test set was approximately 90 minutes in length and comprised of 8˜11-minutes meeting excerpts collected at CMU, ICSI, the LDC, and NIST.

Program

The proceedings for the ICASSP workshop are now available.

Workshop Proceedings

Notebooks with the workshop papers were provided at the workshop to attendees. The proceedings of this workshop will be formally published as a NIST Special Publication after the workshop.

Contact information

Contact rteval@nist.gov for further information.

NIST Automatic Meeting Transcription Data Collection and Annotation Workshop (Nov. 2, 2001)

An initial informal workshop was held at NIST on November 2, 2001 to explore a collaboration among sites collecting meeting room corpora. The sites in attendance included Carnegie Mellon University, the University of California at Berkeley - International Computer Science Institute, Johns Hopkins University, the MITRE Corporation, the Linguistic Data Consortium, the University of Washington, and the host site: the National Institute of Standards and Technology.

The workshop addressed issues in data collection and annotation approaches, data sharing, common annotation standards and tools, and distribution of corpora. Great enthusiasm was expressed by all of the sites to create a collaborative project where data could be shared via a set of common standards. There was also consensus that each of the sites would make their data available to the Linguistic Data Consortium for public distribution. The presentation slides from the workshop are included below as PDF documents. They are the property of the contributing sites and should not be copied or re-distributed without their express permission.