Speech recognitionwith segmental conditional random fields: A summary of the JHU CLSP 2010 Summer Workshop
Geoffrey Zweig, P. Nguyen, Dirk Van Compernolle et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 2011
This paper summarizes the 2010 CLSP Summer Workshop on speech recognition at Johns Hopkins University. The key theme of the workshop was to improve on state-of-the-art speech recognition systems by using Segmental Conditional Random Fields (SCRFs) to integrate multiple types of information. This approach uses a state of-the-art baseline as a springboard from which to add a suite of novel features including ones derived from acoustic templates, deep neural net phoneme detections, duration models, modulation features, and whole word point-process models. The SCRF framework is able to appropriately weight these different information sources to produce significant gains on both die Broadcast News and Wall Street Journal tasks.
Cited by 37 works. doi:10.1109/icassp.2011.5947490
Authors
- Geoffrey Zweig
- P. Nguyen
- Dirk Van Compernolle
- Kris Demuynck
- Les Atlas
- Pascal Clark
- Gregory Sell
- M. Wang
- Fei Sha
- Hynek Hermansky B
- Damianos Karakos
- Samuel Thomas
- Garimella S. V. S. Sivaram
- Samuel R. Bowman
- Justine Kao
References
- Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
- Semi-Markov Conditional Random Fields for Information Extraction
- A segmental CRF approach to large vocabulary continuous speech recognition
- Advances in speech transcription at IBM under the DARPA EARS program
- Template-Based Continuous Speech Recognition
- SCARF: a segmental conditional random field toolkit for speech recognition
- Phoneme recognition using spectral envelope and modulation frequency features
- SPRAAK : an open source ‘SPeech Recognition and Automatic Annotation Kit’
- Point Process Models for Spotting Keywords in Continuous Speech
- Augmented Statistical Models for Speech Recognition