J
J. Makhoul
Researcher at Verizon Communications
Publications - 23
Citations - 954
J. Makhoul is an academic researcher from Verizon Communications. The author has contributed to research in topics: Word error rate & Hidden Markov model. The author has an hindex of 16, co-authored 23 publications receiving 943 citations.
Papers
More filters
Proceedings ArticleDOI
A segment vocoder at 150 b/s
TL;DR: It is demonstrated in this paper that this random quantizer used in the original vocoder is near-optimal by comparing it with quantizers that use clustering algorithms for quantizing speech segments.
Patent
Language-independent and segmentation-free optical character recognition system and method
J. Makhoul,Richard Schwartz +1 more
TL;DR: In this article, a language-independent and segment free OCR system and method comprises a unique feature extraction approach which represents two dimensional data relating to OCR as one independent variable (specifically the position within a line of text in the direction of the line) so that the same CSR technology based on HMMs can be adapted in a straightforward manner to recognize optical characters.
Proceedings ArticleDOI
Batch, incremental and instantaneous adaptation techniques for speech recognition
TL;DR: It is shown that sizable gains can be achieved by either batch or incremental adaptation for large vocabulary recognition of native speakers, and that good improvements in performance are realized when instantaneous adaptation is used for recognition of non-native speakers.
Proceedings ArticleDOI
The role of word-dependent coarticulatory effects in a phoneme-based speech recognition system
Yen-Lu Chow,Richard Schwartz,S. Roucos,Owen Kimball,Patti Price,Francis Kubala,M. Dunham,M. Krasner,J. Makhoul +8 more
TL;DR: This paper describes the results of the work in designing a system for large-vocabulary word recognition of continuous speech, and generalizes the use of context-dependent Hidden Markov Models of phonemes to take into account word-dependent coarticulatory effects.
Proceedings ArticleDOI
Comparative experiments on large vocabulary speech recognition
TL;DR: Four specific problem areas sharing the common thread that the test condition exposes the recognizer to phenomena not observed in the training data are focused on, including words outside the vocabulary, spoken language effects due to subject variability and spontaneous dictation, and new microphones not used in training.