Speech Recognition Using Broad Classes
Applications of Broad Class Knowledge for Noise Robust Speech Recognition
978-3-639-27976-4
363927976X
172
2010-07-28
68.00 €
eng
https://images.our-assets.com/cover/230x230/9783639279764.jpg
https://images.our-assets.com/fullcover/230x230/9783639279764.jpg
https://images.our-assets.com/cover/2000x/9783639279764.jpg
https://images.our-assets.com/fullcover/2000x/9783639279764.jpg
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.
https://www.morebooks.de/books/ru/published_by/vdm-verlag-dr-mueller/3/products
Электроника, электротехника, коммуникационные технологии
https://www.morebooks.de/store/ru/book/speech-recognition-using-broad-classes/isbn/978-3-639-27976-4