• Corpus ID: 5905597

The ICSI Meeting Project: Resources and Research

  title={The ICSI Meeting Project: Resources and Research},
  author={Adam L. Janin and Jeremy Ang and Sonali Bhagat and Rajdip Dhillon and Jane Edwards and J. Marcias-Guarasa and Nelson Morgan and Barbara Peskin and Elizabeth Shriberg and Andreas Stolcke and Chuck Wooters and Britta Wrede},
This paper provides a progress report on ICSI s Meeting Project, including both the data collected and annotated as part of the pro-ject, as well as the research lines such materials support. We include a general description of the official ICSI Meeting Corpus , as currently available through the Linguistic Data Consortium, discuss some of the existing and planned annotations which augment the basic transcripts provided there, and describe several research efforts that make use of these… 

Tables from this paper

Issues in meeting transcription - the ISL meeting transcription system

This paper describes the Interactive Systems Lab’s Meeting transcription system, which performs segmentation, speaker clustering as well as transcriptions of conversational meeting speech, and investigates the effects of automatic segmentation on adaptation.


This paper describes the speech recognition (STT) part of the Interactive Systems Lab’s 2004 Meeting transcription system, for the IPM, SDM, and MDM conditions; which was evaluated in NIST's RT-04S “Meeting” evaluation.


The sentence segmentation performance is significantly improved by the adapted classification model compared to the one obtained by using in-domain data only, independently of the amount of in- domain data used.

The Rich Transcription 2005 Spring Meeting Recognition Evaluation

This paper presents the design and results of the Rich Transcription Spring 2005 (RT-05S) Meeting Recognition Evaluation. This evaluation is the third in a series of community-wide evaluations of


This paper overviews recent progress in the development of corpus-based spontaneous speech recognition technology focusing on various achievements of a Japanese 5-year national project “Spontaneous

The CALO Meeting Assistant System

The CALO-MA architecture and its speech recognition and understanding components, which include real-time and offline speech transcription, dialog act segmentation and tagging, topic identification and segmentation, question-answer pair identification, action item recognition, decision extraction, and summarization are presented.

Answering questions about archived, annotated meetings

It is concluded that natural language interfaces to meeting archives are useful, but that more experimental work is needed to find ways to incent users to take advantage of the expressive power of natural language when asking questions about meetings.

Manual Annotation of Opinion Categories in Meetings

Modifications to the coding guidelines that were required to extend the categories from an opinion annotation scheme developed for monologue text to the genre of multiparty meetings are described and the results of an inter-annotator agreement study are presented.

Multimodal Meeting Capture and Understanding with the CALO Meeting Assistant

The CALO Meeting Assistant aims to reach beyond an intelligent room that understands only the activities of people in meetings, and attempts to understand their overarching concerns and interpret their behaviors from the perspective of what their meetings mean to them.

Robust Speaker Diarization for meetings

Four of the main improvements to the ICSI speaker diarization system submitted for the NIST Rich Transcription evaluation (RT06s) conducted on the meetings environment are introduced: a new training-free speech/non-speech detection algorithm, the introduction of a new algorithm for system initialization, and a frame purification algorithm to increase clusters differentiability.

Meetings about meetings: research at ICSI on speech in multiparty conversations

  • N. MorganD. Baron Chuck Wooters
  • Mathematics
    2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).
  • 2003
Progress is reported on the collection and subsequent release of a 75-meeting corpus, the development of a prosodic database for a large subset of these meetings, and the improvement of both near-mic and far-mic speech recognition results for meeting speech test sets.

The ICSI Meeting Corpus

  • Adam L. JaninD. Baron Chuck Wooters
  • Computer Science
    2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).
  • 2003
A corpus of data from natural meetings that occurred at the International Computer Science Institute in Berkeley, California over the last three years is collected, which supports work in automatic speech recognition, noise robustness, dialog modeling, prosody, rich transcription, information retrieval, and more.

Meeting Recorder Project: Dialog Act Labeling Guide

The tagset for labeling meetings presented here has been modified as necessary to better reflect the types of interaction the authors observed in multiparty face-to-face meetings.

The ICSI Meeting Recorder Dialog Act (MRDA) Corpus

A new corpus of over 180,000 hand- annotated dialog act tags and accompanying adjacency pair annotations for roughly 72 hours of speech from 75 naturally-occurring meetings is described.

The Meeting Project at ICSI

The vision of the task, the challenges it represents, and the current state of the development are given, with particular attention to automatic transcription.

From switchboard to meetings: development of the 2004 ICSI-SRI-UW meeting recognition system

The paper describes the system devised for recognizing speech in meetings, which was an entry in the NIST Spring 2004 Meeting Recognition Evaluation, and a modified MAP adaptation procedure was developed to make best use of discriminatively trained (MMIE) prior models.

Audio information access from meeting rooms

  • S. RenalsD. Ellis
  • Computer Science
    2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).
  • 2003
We investigate approaches to accessing information from the streams of audio data that result from multi-channel recordings of meetings. The methods investigated use word-level transcriptions, and

Relationship between dialogue acts and hot spots in meetings

  • B. WredeElizabeth Shriberg
  • Psychology
    2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721)
  • 2003
It is found that perplexities are similar for involved and non-involved utterances, and suggests that it may not be the amount of propositional content, but rather participants' attitudes toward that content, that differentiates hot spots from other regions in a meeting.

Observations on overlap: findings and implications for automatic processing of multi-party conversation

It is suggested that overlap is an important inherent characteristic of conversational speech that should not be ignored; on the contrary, it should be jointly modeled with acoustic and language model information in machine processing of conversation.

Spotting "hot spots" in meetings: human judgments and prosodic cues

It is suggested that humans do agree to some extent on the judgment ofhot spots, and that acoustic-only cues could be used for automatic detection of hot spots in natural meetings.