- Abstract:
-
This paper describes the AMI transcription system for speech in meetings developed in collaboration by five research groups. The system includes generic techniques such as discriminative and speaker adaptive training, vocal tract length normalisation, heteroscedastic linear discriminant analysis, maximum likelihood linear regression, and phone posterior based features, as well as techniques specifi- cally designed for meeting data. These include segmentation and cross-talk suppression, beam-forming, domain adaptation, web-data collection, and channel adaptive training. The system was improved by more than 20% relative in word error rate compared to our previous system and was used in the NIST RT 06 evaluations where it was found to yield competitive performance.
- Links To Paper
- No links available
- Bibtex format
- @InProceedings{EDI-INF-RR-1002,
- author = {
Thomas Hain
and Lukas Burget
and John Dines
and Giulia Garau
and Michael Lincoln
and Jithendra Vepa
and Martin Karafiat
},
- title = {The AMI System For The Transcription Of Speech In Meetings},
- book title = {International Conference on Acoustics, Speech, and Signal Processing},
- publisher = {IEEE},
- year = 2007,
- volume = {IV},
- pages = {357-360},
- doi = {10.1109/ICASSP.2007.366923},
- }
|