@inbook{46b98235579c4542962e6a4d9f708cec,
title = "The Development of the AMI System for the Transcription of Speech in Meetings",
abstract = "The automatic processing of speech collected in conference style meetings has attracted considerable interest with several large scale projects devoted to this area. This paper describes the development of a baseline automatic speech transcription system for meetings in the context of the AMI (Augmented Multiparty Interaction) project. We present several techniques important to processing of this data and show the performance in terms of word error rates (WERs). An important aspect of transcription of this data is the necessary flexibility in terms of audio pre-processing. Real world systems have to deal with flexible input, for example by using microphone arrays or randomly placed microphones in a room. Automatic segmentation and microphone array processing techniques are described and the effect on WERs is discussed. The system and its components presented in this paper yield competitive performance and form a baseline for future research in this domain.",
author = "Thomas Hain and Luk{\'a}{\v s} Burget and John Dines and Iain McCowan and Giulia Garau and Martin Karafiat and Mike Lincoln and Darren Moore and Vincent Wan and Roeland Ordelman and Steve Renals",
year = "2006",
doi = "10.1007/11677482\_30",
language = "English",
isbn = "978-3-540-32549-9",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "344--356",
editor = "Steve Renals and Samy Bengio",
booktitle = "Machine Learning for Multimodal Interaction",
address = "United Kingdom",
note = "Second International Workshop (MLMI 2005) ; Conference date: 11-07-2005 Through 13-07-2005",
}