Name
Abstract | ||
|---|---|---|
This paper presents the results of our experiments on bottleneck feature applied to a wMVDR (Warped Minimum Variance Distortionless Response) frontend. We examine how to best optimize wMVDR-BNF features and wMVDR combined with MFCC bottleneck features (wMVDR+MFCC-BNF). Our wMVDR+MFCC-BNF frontend improves a single pass system from 18.7% (20.7%) to 18.1% compared to a MFCC-BNF (MFCC) system tested on the Quaero 2010 German evaluation set. When used in a system combination our wMVDR-BNF and wMVDR+MFCC-BNF systems reduced the overall WER from 14.3% to 13.3% on the IWSLT 2010 test set while at the same time reducing the number of systems needed from 9 to 5. Our result of 11.9% on the 2012 IWSLT testset is better than the best result submitted during the evaluation campaign. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/ICASSP.2013.6639017 | ICASSP |
Keywords | Field | DocType |
wmvdr+mfcc-bnf frontend,lvcsr,speech recognition,bottle neck features,iwslt 2010 test set,evaluation campaign,wmvdr,asr,mlp,bnf,warped minimum variance distortionless response frontend,bottleneck features,quaero 2010 german evaluation set,wer,speech,mel frequency cepstral coefficient | Single pass,Bottleneck,Mel-frequency cepstrum,Minimum-variance unbiased estimator,System combination,Pattern recognition,Computer science,Speech recognition,Artificial intelligence,Test set | Conference |
ISSN | Citations | PageRank |
1520-6149 | 2 | 0.43 |
References | Authors | |
8 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Kevin Kilgour | 1 | 54 | 11.00 |
| Igor Tseyzer | 2 | 2 | 0.77 |
| Quoc Bao Nguyen | 3 | 30 | 4.67 |
| Alex Waibel | 4 | 6343 | 1980.68 |