@InProceedings{Evin2010_564,
<br/>   author = {Diego Evin and Jorge Gurlekian and Humberto Torres},
<br/>   booktitle = {Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2010},
<br/>   title = {N-Best Rescoring based on Intonation Prediction for a Spanish ASR System},
<br/>   year = {2010},
<br/>   editor = {Hansjörg Mixdorff},
<br/>   month = mar,
<br/>   pages = {234--233},
<br/>   publisher = {TUDpress, Dresden},
<br/>   abstract  = {This paper presents a novel method for rescoring the n-best recognition
hypotheses using intonation knowledge. The model synthesizes the f0 contours for
each of the n-best hypotheses and estimates an intonative matching index between
the synthetic shapes and the real f0 contour. This index is applied in the rescoring
process, and can be viewed as a degree of intonation compatibility between the
hypotheses and the input sentence. The f0 prediction is based on classification and
regression trees and the Fujisaki model. We evaluate our approach using a single
speaker of the Buenos Aires Spanish LIS-SECYT database under clean and babblenoisy
conditions. Considering the systems under no grammar condition, the proposed
model reduces the mean absolute word error rate in 3.1% with respect to the baseline
system, in a consistent manner and under different noise conditions.},
<br/>   isbn = {978-3-941298-85-9},
<br/>   issn = {0940-6832},
<br/>   keywords = {Speech Recognition},
<br/>   url = {https://www.essv.de/pdf/2010_234_233.pdf},
<br/>}