Applying Large Vocabulary Hybrid HMM-MLP Methods to Telephone Recognition of Digits and Natural Numbers

TitleApplying Large Vocabulary Hybrid HMM-MLP Methods to Telephone Recognition of Digits and Natural Numbers
Publication TypeTechnical Report
Year of Publication1995
AuthorsMa, K. W.
Other Numbers964
Abstract

The hybrid Hidden Markov Model (HMM) / Neural Network (NN) speech recognition system at the International Computer Science Institute (ICSI) uses a single hidden layer MLP (Multi Layer Perceptron) to compute the emission probabilities of the states of the HMM. This recognition approach was developed and has traditionally been used for large vocabulary size continuous speech recognition. In this report, however, such a recognition scheme is applied directly to three much smaller vocabulary size corpora, the Bellcore isolated digits, the TI connected digits, and the Center for Spoken Language Understanding Numbers'93 database. The work reported here is not only on developing small baseline systems to facilitate all future research experiments, but also on using these systems to evaluate front-end research issues, and the feasibility of using context-dependency for speech recognition under the hybrid approach developed at ICSI. In addition, using the TI connected digits, the performance of ICSI's baseline system on small vocabulary size speaker-independent task is compared with those of other speech research institutes.

URLhttp://www.icsi.berkeley.edu/ftp/global/pub/techreports/1995/tr-95-024.pdf
Bibliographic Notes

ICSI Technical Report TR-95-024

Abbreviated Authors

K. W. Ma

ICSI Publication Type

Technical Report