If you made any changes in Pure, your changes will be visible here soon.

Research Output 1998 2019

Filter
Paper
2019

Fast generation for convolutional autoregressive models

Ramachandran, P., Le Paine, T., Khorrami, P., Babaeizadeh, M., Chang, S., Zhang, Y., Hasegawa-Johnson, M., Campbell, R. & Huang, T., Jan 1 2019.

Research output: Contribution to conferencePaper

training method
performance
Nave
Model-making
Cache
2014

Singing-voice separation from monaural recordings using deep recurrent neural networks

Huang, P. S., Kim, M., Hasegawa-Johnson, M. A. & Smaragdis, P., Jan 1 2014, p. 477-482. 6 p.

Research output: Contribution to conferencePaper

Recurrent neural networks
Source separation
Recurrent Neural Networks
2011

Multimodal speech and audio user interfaces for K-12 outreach

Hasegawa-Johnson, M. A., Goudeseune, C., Cole, J., Kaczmarski, H., Kim, H., King, S., Mahrt, T., Huang, J. T., Zhuang, X., Lin, K. H., Sharma, H. V., Li, Z. & Huang, T. S., Dec 1 2011, p. 526-531. 6 p.

Research output: Contribution to conferencePaper

Motorcycles
Speech recognition
User interfaces
Clocks
2010

A minimum converted trajectory error (MCTE) approach to high quality speech-to-lips conversion

Zhuang, X., Wang, L., Soong, F. & Hasegawa-Johnson, M., Dec 1 2010, p. 1736-1739. 4 p.

Research output: Contribution to conferencePaper

Lip
Linguistics
Joints
Phonetics
Trajectory

A procedure for estimating gestural scores from natural speech

Nam, H., Mitra, V., Tiede, M., Saltzman, E., Goldstein, L., Espy-Wilson, C. & Hasegawa-Johnson, M., Dec 1 2010, p. 30-33. 4 p.

Research output: Contribution to conferencePaper

Gestures
Acoustics
Natural Speech
Gesture
Word Recognition

FSM-based pronunciation modeling using articulatory phonological code

Hu, C., Zhuang, X. & Hasegawa-Johnson, M. A., Dec 1 2010, p. 2274-2277. 4 p.

Research output: Contribution to conferencePaper

Vocabulary
Activation
Modeling
Onset
Experiment

Kinematic analysis of tongue movement control in spastic dysarthria

Kim, H., Rong, P., Loucks, T. M. & Hasegawa-Johnson, M., Dec 1 2010, p. 2578-2581. 4 p.

Research output: Contribution to conferencePaper

Dysarthria
Tongue
Biomechanical Phenomena
Cerebral Palsy
Kinematics

Robust automatic speech recognition with decoder oriented ideal binary mask estimation

Kim, L. H., Kim, K. T. & Hasegawa-Johnson, M. A., Dec 1 2010, p. 2066-2069. 4 p.

Research output: Contribution to conferencePaper

Masks
Noise
Music
Joints
Automatic Speech Recognition

Semi-supervised training of Gaussian mixture models by conditional entropy minimization

Huang, J. T. & Hasegawa-Johnson, M. A., Dec 1 2010, p. 1353-1356. 4 p.

Research output: Contribution to conferencePaper

Entropy
Phonetics
Mixture Model
2005

Distinctive feature based SVM discriminant features for improvements to phone recognition on telephone band speech

Borys, S. & Hasegawa-Johnson, M. A., Dec 1 2005, p. 697-700. 4 p.

Research output: Contribution to conferencePaper

Telephone
Support vector machines
2004

A factorial HMM approach to robust isolated digit recognition in background music

Deoras, A. N. & Hasegawa-Johnson, M., Jan 1 2004, p. 2093-2096. 4 p.

Research output: Contribution to conferencePaper

music
Hidden Markov Model
Music
Signal-to-noise Ratio
Utterance

Automatic detection of contrast for speech understanding

Zhang, T., Hasegawa-Johnson, M. A. & Levinson, S. E., Jan 1 2004, p. 581-584. 4 p.

Research output: Contribution to conferencePaper

spoken language
neural network
event
knowledge
Spoken Language

AVICAR: Audio-Visual Speech Corpus in a Car Environment

Lee, B., Hasegawa-Johnson, M. A., Goudeseune, C., Kamdar, S., Borys, S., Liu, M. & Huang, T. S., Jan 1 2004, p. 2489-2492. 4 p.

Research output: Contribution to conferencePaper

video
language
Car
Audiovisual Speech
Signal-to-noise Ratio

Children's emotion recognition in an intelligent tutoring scenario

Zhang, T., Hasegawa-Johnson, M. & Levinson, S. E., Jan 1 2004, p. 1441-1444. 4 p.

Research output: Contribution to conferencePaper

emotion
scenario
confidence
Emotion
Emotion Recognition

Intertranscriber reliability of prosodic labeling on telephone conversation using ToBI

Yoon, T. J., Chavarría, S., Cole, J. & Hasegawa-Johnson, M., Jan 1 2004, p. 2729-2732. 4 p.

Research output: Contribution to conferencePaper

telephone
conversation
event
statistics
ToBI

Modeling and recognition of phonetic and prosodic factors for improvements to acoustic speech recognition models

Borys, S., Hasegawa-Johnson, M., Cole, J. & Cohen, A., Jan 1 2004, p. 3013-3016. 4 p.

Research output: Contribution to conferencePaper

phonetics
acoustics
Speech Recognition
Acoustics
Modeling

Modeling pronunciation variation using artificial neural networks for English spontaneous speech

Chen, K. & Hasegawa-Johnson, M. A., Jan 1 2004, p. 1461-1464. 4 p.

Research output: Contribution to conferencePaper

neural network
vocabulary
experiment
Artificial Neural Network
Modeling

Semantic analysis for a speech user interface in an intelligent tutoring system

Ren, Y., Hasegawa-Johnson, M. A. & Levinson, S. E., Dec 1 2004, p. 313-315. 3 p.

Research output: Contribution to conferencePaper

Intelligent systems
User interfaces
Semantics
Acoustics

Source separation using particle filters

Gandhi, M. A. & Hasegawa-Johnson, M. A., Jan 1 2004, p. 2673-2676. 4 p.

Research output: Contribution to conferencePaper

non-linear model
estimation procedure
system model
statistical method
Filter

Stop consonant classification by dynamic formant trajectory

Zheng, Y., Hasegawa-Johnson, M. & Borys, S., Jan 1 2004, p. 2481-2484. 4 p.

Research output: Contribution to conferencePaper

candidacy
Formants
Stop Consonants
Trajectory
Invariance
2003

Maximum conditional mutual information projection for speech recognition

Omar, M. K. & Hasegawa-Johnson, M., Jan 1 2003, p. 505-508. 4 p.

Research output: Contribution to conferencePaper

discriminant analysis
Discriminant analysis
Speech recognition
projection
Maximum likelihood estimation

Non-linear maximum likelihood feature transformation for speech recognition

Omar, M. K. & Hasegawa-Johnson, M., Jan 1 2003, p. 2497-2500. 4 p.

Research output: Contribution to conferencePaper

Hidden Markov models
Speech recognition
Maximum likelihood
Acoustics
Independent component analysis

Prosody dependent speech recognition with explicit duration modelling at intonational phrase boundaries

Chen, K., Borys, S., Hasegawa-Johnson, M. & Cole, J., Jan 1 2003, p. 393-396. 4 p.

Research output: Contribution to conferencePaper

Speech recognition
Hidden Markov models
Acoustics
acoustics
Labeling
2002

An evaluation of using mutual information for selection of acoustic-features representation of phonemes for speech recognition

Omar, M. K., Chen, K., Hasegawa-Johnson, M. & Brandman, Y., Jan 1 2002, p. 2129-2132. 4 p.

Research output: Contribution to conferencePaper

acoustics
evaluation
divergence
Evaluation
Speech Recognition