Multi-stream Features Combination based on Dempster-Shafer Rule for LVCSR System
This paper investigates the combination of two streams of acoustic features. Extending our previous work on small vocabulary task, we show that combination based on Dempster-Shafer rule outperforms several classical rules like sum, product and inverse entropy weighting even in LVCSR systems. We analyze results in terms of Frame Error Rate and Cross Entropy measures. Experimental framework uses meeting transcription task and results are provided on RT05 evaluation data. Results are consistent with what has been previously observed on smaller databases.
Submitted for publication
Record created on 2010-02-11, modified on 2016-08-08