Bookcover of Speech Recognition Using Broad Classes
Booktitle:

Speech Recognition Using Broad Classes

Applications of Broad Class Knowledge for Noise Robust Speech Recognition

VDM Verlag Dr. Müller (2010-07-28 )

Books loader

Omni badge eligible for voucher
ISBN-13:

978-3-639-27976-4

ISBN-10:
363927976X
EAN:
9783639279764
Book language:
English
Blurb/Shorttext:
This work explores the use of speech knowledge for robust speech recognition by first describing the speech signal through a set of broad speech units, and then conducting a more detailed analysis from these broad units. These units are formed by grouping together parts of the acoustic signal that have similar temporal and spectral characteristics. This work first introduces a novel instantaneous adaptation technique to robustly detect broad classes (BCs) from the input signal using the Extended Baum-Welch (EBW) transformations. Recognition experiments indicate that the EBW method offers a 5% relative improvement compared to typical adaptation approaches. Next, we explore utilizing BC knowledge as a pre-processor for segment-based speech recognition systems. Recognition experiments indicate that utilizing BC knowledge as a pre- processor offers a 14% relative improvement over the baseline recognizer in noisy conditions. Finally, this thesis investigates using BC knowledge for island-driven search. Experiments indicate that the island-driven search strategy results in a 3% improvement in accuracy and also provides faster computation time.
Publishing house:
VDM Verlag Dr. Müller
Website:
http://www.vdm-verlag.de
By (author) :
Tara Sainath
Number of pages:
172
Published at:
2010-07-28
Stock:
Available
Category:
Electronics, electro-technology, communications technology
Price:
68.00 €
Keywords:
Speech recognition, Noise robustness, Optimization, Adaptation

Books loader

Newsletter

Adyen::amex Adyen::mc Adyen::visa Adyen::cup Adyen::unionpay Paypal Wire Transfer

  0 products in the shopping cart
Edit cart
Loading frontend
LOADING