Edinburgh Research Explorer

The 2005 AMI System for the transcription of Speech in Meetings

Research output: Chapter in Book/Report/Conference proceedingConference contribution

  • T. Hain
  • L. Burget
  • J. Dines
  • G. Garau
  • Martin Karafiat
  • M. Lincoln
  • I. McCowan
  • Darren Moore
  • V. Wan
  • R. Ordelman
  • S. Renals

Related Edinburgh Organisations

Documents

Original languageEnglish
Title of host publicationProceedings of the Rich Transcription 2005 Spring Meeting Recognition Evaluation
Number of pages12
Publication statusPublished - 2005

Abstract

In this paper we describe the 2005 AMI system for the transcription of speech in meetings used in the 2005 NIST RT evaluations. The system was designed for participation in the speech to text part of the evaluations, in particular for transcription of speech recorded with multiple distant microphones and independent headset microphones. System performance was tested on both conference room and lecture style meetings. Although input sources are processed using different frontends, the recognition process is based on a unified system architecture. The system operates in multiple passes and makes use of state of the art technologies such as discriminative training, vocal tract length normalisation, heteroscedastic linear discriminant analysis, speaker adaptation with maximum likelihood linear regression and minimum word error rate decoding. In this paper we describe the system performance on the official development and test sets for the NIST RT05s evaluations. The system was jointly developed in less than 10 months by a multi-site team and was shown to achieve competitive performance.

Download statistics

No data available

ID: 27399947