New results with the Lincoln tied-mixture HMM CSR system
HLT '91 Proceedings of the workshop on Speech and Natural Language
Experience with a stack decoder-based HMM CSR and back-OFF N-gram language models
HLT '91 Proceedings of the workshop on Speech and Natural Language
A rapid match algorithm for continuous speech recognition
HLT '90 Proceedings of the workshop on Speech and Natural Language
Automatic Speech Recognition: The Development of the Sphinx Recognition System
Automatic Speech Recognition: The Development of the Sphinx Recognition System
A CSR-NL interface specification version 1.5
HLT '89 Proceedings of the workshop on Speech and Natural Language
DARPA February 1992 pilot corpus CSR "dry run" benchmark test results
HLT '91 Proceedings of the workshop on Speech and Natural Language
The Lincoln large-vocabulary stack-decoder HMM CSR
ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II
| Hi-index | 0.01 |
The work described here focuses on recognition of the Wall Street Journal (WSJ) pilot database [17], a new CSR database which supports 5K, 20K, and up to 64K- word CSR tasks. The original Lincoln Tied-Mixture HMM CSR was implemented using a time-synchronous beam-pruned search of a static network [14] and does not extend well to this task because the recognition network would be too large for currently practical workstations. Therefore, the recognizer has been converted to a stack decoder-based search strategy[1,7,16]. This decoder has been shown to function effectively on up to 64K-word recognition of continuous speech. This paper describes the acoustic modeling techniques and the implementation of the stack decoder used to obtain these results.