Abstract
This paper presents a study on finite-register-length effects in a Hidden Markov Model speech recognizer. A statistic model is utilized to approximate the distribution of the score differences. The range of recognition rate due to quantization noise on HMM parameters is calculated by using the statistic model. Then the relation between the recognition rate and the quantization noise is derived. This provides the information for determining the register length in the hardware realization of a HMM speech recognizer.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
