Search

Your search keyword '"Ki-Seung Lee"' showing total 4 results
Start Over Author "Ki-Seung Lee" Publisher institute of electronics, information and communications engineers (ieice)
Sorry, I don't understand your search. ×
4 results on '"Ki-Seung Lee"'

1. Silent Speech Interface Using Ultrasonic Doppler Sonar

Author

Ki-Seung Lee

Subjects
Silent speech interface, Artificial Intelligence, Hardware and Architecture, Computer science, Acoustics, Ultrasonic doppler, Deep neural networks, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering, Sonar, Software
Published
2020
Full Text
View/download PDF

2. HMM-Based Maximum Likelihood Frame Alignment for Voice Conversion from a Nonparallel Corpus

Author

Ki-Seung Lee

Subjects
Computer science, Maximum likelihood, Speech recognition, Frame (networking), 020206 networking & telecommunications, 02 engineering and technology, 030507 speech-language pathology & audiology, 03 medical and health sciences, Artificial Intelligence, Hardware and Architecture, Maximum likelihood criterion, 0202 electrical engineering, electronic engineering, information engineering, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering, 0305 other medical science, Hidden Markov model, Software
Published
2017
Full Text
View/download PDF

3. Compensation for Shot-to-Shot Variations in Laser Pulse Energy for Photoacoustic Imaging

Author

Ki-Seung Lee

Subjects
Photoacoustic effect, Materials science, business.industry, Photoacoustic imaging in biomedicine, 02 engineering and technology, Laser, Electronic, Optical and Magnetic Materials, Compensation (engineering), law.invention, Photoacoustic Doppler effect, 020210 optoelectronics & photonics, Optics, law, Shot (pellet), 0202 electrical engineering, electronic engineering, information engineering, Electrical and Electronic Engineering, business, Pulse energy
Published
2017
Full Text
View/download PDF

4. Robust Recognition of Fast Speech

Author

Ki-Seung Lee

Subjects
Signal processing, Voice activity detection, Degree (graph theory), Computer science, Speech recognition, Maximum likelihood, Word error rate, Speech processing, Artificial Intelligence, Hardware and Architecture, Cepstrum, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering, Software, Utterance
Abstract

This letter describes a robust speech recognition system for recognizing fast speech by stretching the length of the utterance in the cepstrum domain. The degree of stretching for an utterance is determined by its rate of speech (ROS), which is based on a maximum likelihood (ML) criterion. The proposed method was evaluated on 10-digits mobile phone numbers. The results of the simulation show that the overall error rate was reduced by 17.8% when the proposed method was employed.

Published
2006
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results