Spontaneous speech recognition using HMMs
Author(s)Yoder, Benjamin W. (Benjamin Wesley), 1977-
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
MetadataShow full item record
This thesis describes a speech recognition system that was built to support spontaneous speech understanding. The system is composed of (1) a front end acoustic analyzer which computes Mel-frequency cepstral coefficients, (2) acoustic models of context-dependent phonemes (triphones), (3) a back-off bigram statistical language model, and (4) a beam search decoder based on the Viterbi algorithm. The contextdependent acoustic models resulted in 67.9% phoneme recognition accuracy on the standard TIMIT speech database. Spontaneous speech was collected using a "Wizard of Oz" simulation of a simple spatial manipulation game. Naive subjects were instructed to manipulate blocks on a computer screen in order to solve a series of geometric puzzles using only spoken commands. A hidden human operator performed actions in response to each spoken command. The speech from thirteen subjects formed the corpus for the speech recognition results reported here. Using a task-specific bigram statistical language model and context-dependent acoustic models, the system achieved a word recognition accuracy of 67.6%. The recognizer operated using a vocabulary of 523 words. The recognition had a word perplexity of 36.
Thesis (M.Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, February 2003.Includes bibliographical references (leaf 63).
DepartmentMassachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology
Electrical Engineering and Computer Science.