Reducing computational complexities of exemplar-based sparse representations with applications to large vocabulary speech recognition

2011 ◽  
Author(s):  
Tara N. Sainath ◽  
Bhuvana Ramabhadran ◽  
David Nahamoo ◽  
Dimitri Kanevsky
Keyword(s):  
Speech Recognition ◽  
Sparse Representations ◽  
Large Vocabulary ◽  
Large Vocabulary Speech Recognition

Large-vocabulary speech recognition algorithms

Computer ◽  
2002 ◽  
Vol 35 (3) ◽  
pp. 42-50 ◽  
Author(s):  
M. Padmanabhan ◽  
M. Picheny
Keyword(s):  
Speech Recognition ◽  
Large Vocabulary ◽  
Recognition Algorithms ◽  
Large Vocabulary Speech Recognition

A unified framework for large vocabulary speech recognition of mutually unintelligible Chinese "regionalects"

2004 ◽  
Author(s):  
Ren-Yuan Lyu ◽  
Dau-Cheng Lyu ◽  
Min-Siong Liang ◽  
Min-Hong Wang ◽  
Yuang-Chin Chiang ◽  
...  
Keyword(s):  
Speech Recognition ◽  
Unified Framework ◽  
Large Vocabulary ◽  
Large Vocabulary Speech Recognition

FINITELY SUBSEQUENTIAL TRANSDUCERS

2003 ◽  
Vol 14 (06) ◽  
pp. 983-994 ◽  
Author(s):  
CYRIL ALLAUZEN ◽  
MEHRYAR MOHRI
Keyword(s):  
Speech Recognition ◽  
Finite Number ◽  
Efficient Algorithm ◽  
Experimental Results ◽  
Theoretical Formulation ◽  
Large Vocabulary ◽  
Finite State Transducers ◽  
Finite State ◽  
Large Vocabulary Speech Recognition

Finitely subsequential transducers are efficient finite-state transducers with a finite number of final outputs and are used in a variety of applications. Not all transducers admit equivalent finitely subsequential transducers however. We briefly describe an existing generalized determinization algorithm for finitely subsequential transducers and give the first characterization of finitely subsequentiable transducers, transducers that admit equivalent finitely subsequential transducers. Our characterization shows the existence of an efficient algorithm for testing finite subsequentiability. We have fully implemented the generalized determinization algorithm and the algorithm for testing finite subsequentiability. We report experimental results showing that these algorithms are practical in large-vocabulary speech recognition applications. The theoretical formulation of our results is the equivalence of the following three properties for finite-state transducers: determinizability in the sense of the generalized algorithm, finite subsequentiability, and the twins property.

Sign in / Sign up

Export Citation Format

Share Document