Cepstral domain segmental feature vector normalization for noise robust speech recognition
Speech Communication - Special issue on robust speech recognition
Robust automatic speech recognition with missing and unreliable acoustic data
Speech Communication
Acoustic environment classification
ACM Transactions on Speech and Language Processing (TSLP)
Weakly Supervised Top-down Image Segmentation
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Weakly Supervised Scale-Invariant Learning of Models for Visual Recognition
International Journal of Computer Vision
Partly hidden Markov model and its application to speech recognition
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
Hidden Markov models with divergence based vector quantized variances
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
Robotic vocabulary building using extension inference and implicit contrast
Artificial Intelligence
ACORNS - towards computational modeling of communication and recognition skills
COGINF '07 Proceedings of the 6th IEEE International Conference on Cognitive Informatics
Efficient backward decoding of high-order hidden Markov models
Pattern Recognition
Proceedings of the 18th ACM conference on Information and knowledge management
Clustering of time series data-a survey
Pattern Recognition
Weakly supervised learning of part-based spatial models for visual object recognition
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
A study on high-order hidden markov models and applications to speech recognition
IEA/AIE'06 Proceedings of the 19th international conference on Advances in Applied Artificial Intelligence: industrial, Engineering and Other Applications of Applied Intelligent Systems
Cross-situational learning: a mathematical approach
EELC'06 Proceedings of the Third international conference on Emergence and Evolution of Linguistic Communication: symbol Grounding and Beyond
| Hi-index | 0.02 |
An efficient method for weakly supervised pattern discovery and recognition from discrete categorical sequences is introduced. The method utilizes two parallel sources of data: categorical sequences carrying some temporal or spatial information and a set of labeled, but not exactly aligned, contextual events related to the sequences. From these inputs the method builds associative models able to describe systematically co-occurring structures in the input streams. The learned models, based on transitional probabilities of events observed at several different time lags, inherently segment and classify novel sequences into contextual categories. Learning and recognition processes are purely incremental and computationally cheap, making the approach suitable for on-line learning tasks. The capabilities of the algorithm are demonstrated in a keyword learning task from continuous infant-directed speech and a continuous speech recognition task operating at varying noise levels.