%Aigaion2 BibTeX export from Idiap Publications %Tuesday 03 December 2024 06:57:43 PM @INCOLLECTION{Keshet_WILEY-3_2009, author = {Keshet, Joseph}, editor = {Keshet, Joseph and Bengio, Samy}, projects = {Idiap}, title = {A Proposal for a Kernel-based Algorithm for Large Vocabulary Continuous Speech Recognition}, booktitle = {Automatic Speech and Speaker Recognition: Large Margin and Kernel Methods}, year = {2009}, publisher = {John Wiley and Sons}, abstract = {We present a proposal of a kernel-based model for large vocabulary continuous speech recognizer. The continuous speech recognition is described as a problem of finding the best phoneme sequence and its best time span, where the phonemes are generated from all permissible word sequences. A non-probabilistic score is assigned to every phoneme sequence and time span sequence, according to a kernel-based acoustic model and a kernel-based language model. The acoustic model is described in terms of segments, where each segment corresponds to a whole phoneme, and it generalizes Segmental Models for the non-probabilistic setup. The language model is based on discriminative language model recently proposed by Roark et al. (2007). We devise a loss function based on the word error rate and present a large margin training procedure for the kernel models, which aims at minimizing this loss function. Finally, we discuss the practical issues of the implementation of kernel-based continuous speech recognition model by presenting an efficient iterative algorithm and considering the decoding process. We conclude the chapter by a brief discussion on the model limitations and future work. This chapter does not introduce any experimental results.} }