The Lincoln Large-Vocabulary HMM CSR*

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 im-plemented using a time-synchronous beam-pruned search of a static network[14] and does not extend well to this task be-cause the recognition network would be too large for currently practical workstations. Therefore, the recognizer has been converted to a stack decoder-based search strategy[I,7,16]. This decoder has been shown to function effectively on up to 64K-word recognition of continuous peech. This paper describes the acoustic modeling techniques and the imple-mentation of the stack decoder used to obtain these results