An Analysis of Using Semantic Parsing for Speech Recognition (2016)
This thesis explores the use of semantic parsing for improving speech recognition performance. Specifically, it explores how a semantic parser may be used in order to re-rank the n-best hypothesis list generated by an automatic speech recognition system. We also explore how system performance is affected when retraining the system's acoustic model using a portion of the re-ranked data.
View:
PDF
Citation:
Undergraduate Honors Thesis, Computer Science Department, University of Texas at Austin.
Bibtex:

Presentation:
Slides (PPT)
Rodolfo Corona Undergraduate Student rcorona [at] utexas edu