Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

29

INTERSPEECH
2010

favoriteEmaildiscussreport

114views Signal Processing» more INTERSPEECH 2010»

Data pruning for template-based automatic speech recognition

13 years 5 months ago

Data pruning for template-based automatic speech recognition

Download www.esat.kuleuven.be

In this paper we describe and analyze a data pruning method in combination with template-based automatic speech recognition. We demonstrate the positive effects of polishing the template database by minimizing the word error rate scores. Data pruning allowed to effectively reduce the database size, and therefore the model size, by an impressive 30%, with consequent benefits on the computation time and memory usage.

Dino Seppi, Dirk Van Compernolle

Real-time Traffic

Data Pruning Method | INTERSPEECH 2010 | Signal Processing | Template-based Automatic Speech | Word Error Rate |

claim paper

Related Content

» Progress in example based automatic speech recognition

» Combining mixture weight pruning and quantization for smallfootprint speech recognition

» Onthefly lattice rescoring for realtime automatic speech recognition

» Multisensory speech processing incorporating automatically extracted hidden dynamic inform...

» HMMbased automatic visual speech segmentation using facial data

» Automatic Detection of Prominent Words in Russian Speech

» Exploiting multimodal data fusion in robust speech recognition

» A Study of the Influence of Speech Type on Automatic Language Recognition Performance

» Speech Recognition with Missing Data using Recurrent Neural Nets

Post Info
More Details (n/a)

Added	18 May 2011
Updated	18 May 2011
Type	Journal
Year	2010
Where	INTERSPEECH
Authors	Dino Seppi, Dirk Van Compernolle

Comments (0)