论文信息 - The AMIDA 2009 meeting transcription system

The AMIDA 2009 meeting transcription system

We present the AMIDA 2009 system for participation in the NIST RT’2009 STT evaluations. Systems for close-talking, far field and speaker attributed STT conditions are described. Im- provements to our previous systems are: segmentation and diar- isation; stacked bottle-neck posterior feature extraction; fMPE training of acoustic models; adaptation on complete meetings; improvements to WFST decoding; automatic optimisation of decoders and system graphs. Overall these changes gave a 6- 13% relative reduction in word error rate while at the same time reducing the real-time factor by a factor of five and using con- siderably less data for acoustic model training.

[1] Daniel Povey,et al. Improvements to fMPE for discriminative training of features , 2005, INTERSPEECH.

[2] Lukás Burget,et al. The 2005 AMI System for the Transcription of Speech in Meetings , 2005, MLMI.

[3] Richard M. Schwartz,et al. Recent progress on the discriminative region-dependent transform for speech feature extraction , 2006, INTERSPEECH.

[4] Xavier Anguera Miró. ROBUST SPEAKER DIARIZATION FOR MEETINGS , 2006 .

[5] David A. van Leeuwen,et al. The AMI Speaker Diarization System for NIST RT06s Meeting Data , 2006, MLMI.

[6] Jithendra Vepa,et al. The segmentation of multi-channel meeting recordings for automatic speech recognition , 2006, INTERSPEECH.

[7] José Manuel Pardo,et al. Robust Speaker Diarization for meetings , 2006 .

[8] David A. van Leeuwen,et al. The 2007 AMI(DA) System for Meeting Transcription , 2007, CLEAR.

[9] Thomas Hain,et al. Recognition and understanding of meetings the AMI and AMIDA projects , 2007, 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU).

[10] Jean Carletta,et al. Accessing a Large Multimodal Corpus Using an Automatic Content Linking Device , 2009, Multimodal Corpora.

[11] S. King,et al. In Proc. Interspeech , 2009 .

[12] Le Zhang,et al. Real-time ASR from meetings , 2009, INTERSPEECH.

[13] Thomas Hain,et al. Automatic Optimization of Speech Decoder Parameters , 2010, IEEE Signal Processing Letters.