2 |
Incorporating nonverbal features into multimodal models of human-to-human communication
|
|
|
|
In: Theses and Dissertations Available from ProQuest (2008)
|
|
BASE
|
|
Show details
|
|
4 |
Structural event detection for rich transcription of speech
|
|
|
|
In: Theses and Dissertations Available from ProQuest (2004)
|
|
BASE
|
|
Show details
|
|
7 |
The Effect of Pruning and Compression on Graphical Representations of the Output of a Speech Recognizer
|
|
|
|
In: Electrical and Computer Engineering Faculty Research and Publications (2003)
|
|
Abstract:
Large vocabulary continuous speech recognition can benefit from an efficient data structure for representing a large number of acoustic hypotheses compactly. Word graphs or lattices have been chosen as such an efficient interface between acoustic recognition engines and subsequent language processing modules. This paper first investigates the effect of pruning during acoustic decoding on the quality of word lattices and shows that by combining different pruning options (at the model level and word level), we can obtain word lattices with comparable accuracy to the original lattices and a manageable size. In order to use the word lattices as the input for a post-processing language module, they should preserve the target hypotheses and their scores while being as small as possible. In this paper, we introduce a word graph compression algorithm that significantly reduces the number of words in the graphical representation without eliminating utterance hypotheses or distorting their acoustic scores. We compare this word graph compression algorithm with several other lattice size-reducing approaches and demonstrate the relative strength of the new word graph compression algorithm for decreasing the number of words in the representation. Experiments are conducted across corpora and vocabulary sizes to determine the consistency of the pruning and compression results.
|
|
Keyword:
Computer Engineering; Electrical and Computer Engineering; Engineering
|
|
URL: https://epublications.marquette.edu/electric_fac/36 https://epublications.marquette.edu/cgi/viewcontent.cgi?article=1035&context=electric_fac
|
|
BASE
|
|
Hide details
|
|
8 |
Statistical parsing and language modeling based on constraint dependency grammar
|
|
|
|
In: Theses and Dissertations Available from ProQuest (2003)
|
|
BASE
|
|
Show details
|
|
9 |
Investigating Probabilistic Constraint Dependency Grammars in Language Modeling
|
|
|
|
In: Department of Electrical and Computer Engineering Technical Reports (2001)
|
|
BASE
|
|
Show details
|
|
10 |
Familiarity and Pronounceability of Nouns and Names
|
|
|
|
In: Electrical and Computer Engineering Faculty Research and Publications (1999)
|
|
BASE
|
|
Show details
|
|
11 |
Parsing and tagging sentences containing lexically ambiguous and unknown tokens
|
|
|
|
In: Theses and Dissertations Available from ProQuest (1999)
|
|
BASE
|
|
Show details
|
|
14 |
Prosodic disambiguation in automatic speech understanding of Thai
|
|
|
|
In: Theses and Dissertations Available from ProQuest (1995)
|
|
BASE
|
|
Show details
|
|
15 |
Improving hidden Markov models for speech recognition
|
|
|
|
In: Theses and Dissertations Available from ProQuest (1995)
|
|
BASE
|
|
Show details
|
|
18 |
PARSEC: A Constraint-Based Parser for Spoken Language Processing
|
|
|
|
In: Department of Electrical and Computer Engineering Technical Reports (1993)
|
|
BASE
|
|
Show details
|
|
|
|