The 2007 AMI(DA) System for Meeting Transcription

Abstract

Abstract. Meeting transcription is one of the main tasks for large vocabulary automatic speech recognition (ASR) and is supported by several large international projects in the area. The conversational nature, the difficult acoustics, and the necessity of high quality speech transcripts for higher level processing make ASR of meeting recordings an interesting challenge. This paper describes the development and system architecture of the 2007 AMIDA meeting transcription system, the third of such systems developed in a collaboration of six research sites. Different variants of the system participated in all speech to text transcription tasks of the 2007 NIST RT evaluations and showed very competitive performance. The best result was obtained on close-talking microphone data where a final word error rate of 24.9% was obtained.

Transcribing Meetings With the AMIDA Systems

“…Equally test sets for seminar style meetings from the CHIL corpora have been provided. In the past we have shown that the performance of the AMIDA systems on seminar data is strongly correlated to conference room meeting transcription [6], [12]. Hence, we have excluded such data from this paper.…”

“…The second task is segmentation and speaker clustering. In work on the RT'07 system we found a considerable mismatch between requirements for diarization and ASR [6]. ASR systems require clusters of reasonable size and can cope with segments that contain significant amounts of silence.…”

“…The transcription systems presented here are the joint effort of the AMI/AMIDA group, in a close international collaboration that participated in the RT evaluations every year since 2005 [5] with very competitive results in 2007 and 2009, on far and near-field tasks [6]. The rest of the paper is organized as follows: We first discuss data resources available for meeting processing and their properties, with special focus on the AMI corpus.…”

Recognition and understanding of meetings the AMI and AMIDA projects

“…of the system would go beyond of the scope of this paper, the interested reader is referred to [28]. Table 7 shows details for various stages in the system, from the initial decoding with unadapted models to the output of the best branch in the system.…”

On the improvement of modulation features using multi-microphone energy tracking for robust distant speech recognition

“…Several scientific projects [18], [7] and challenges [8], [10] have been launched during the last decade targeting intelligent interfaces for indoors smart environments. Distant speech recognition (DSR) via distributed microphones is examined in most of them.…”