Abstract | ||
---|---|---|
The paper describes our system devised for recognizing speech in meetings, which was an entry in the NIST Spring 2004 Meeting Recognition Evaluation. This system was developed as a collaborative effort between ICSI, SRI, and UW and was based on SRI's 5xRT Conversational Telephone Speech (CTS) recognizer. The CTS system was adapted to the Meetings domain by adapting the CTS acoustic and language models to the Meeting domain, adding noise reduction and delay-sum array processing for far-field recognition, and adding postprocessing for cross-talk suppression for close-talking microphones. A modified MAP adaptation procedure was developed to make best use of discriminatively trained (MMIE) prior models. These meeting-specific changes yielded an overall 9% and 22% relative improvement as compared to the original CTS system, and 16% and 29% relative improvement as compared to our 2002 Meeting Evaluation system, for the individual-headset and multiple-distant microphones conditions, respectively. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1007/978-3-540-30568-2_17 | MLMI |
Keywords | Field | DocType |
cts system,conversational telephone speech,evaluation system,icsi-sri-uw meeting recognition system,nist spring,meetings domain,relative improvement,multiple-distant microphones condition,recognition evaluation,cts acoustic,original cts system,noise reduction,language model | Noise reduction,Array processing,Evaluation system,Map adaptation,Recognition system,Computer science,Speech recognition,NIST,Speaker diarisation,Language model | Conference |
Volume | ISSN | ISBN |
3361 | 0302-9743 | 3-540-24509-X |
Citations | PageRank | References |
3 | 0.57 | 8 |
Authors | ||
10 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chuck Wooters | 1 | 404 | 58.49 |
Nikki Mirghafori | 2 | 209 | 27.18 |
Andreas Stolcke | 3 | 6690 | 712.46 |
Tuomo Pirinen | 4 | 4 | 1.30 |
Ivan Bulyko | 5 | 249 | 22.40 |
Dave Gelbart | 6 | 3 | 0.57 |
Martin Graciarena | 7 | 281 | 24.70 |
Scott Otterson | 8 | 43 | 4.48 |
Barbara Peskin | 9 | 176 | 18.45 |
Mari Ostendorf | 10 | 2462 | 348.75 |