A segmental CRF approach to large vocabulary continuous speech recognition
Citations Over TimeTop 1% of 2009 papers
Abstract
This paper proposes a segmental conditional random field framework for large vocabulary continuous speech recognition. Fundamental to this approach is the use of acoustic detectors as the basic input, and the automatic construction of a versatile set of segment-level features. The detector streams operate at multiple time scales (frame, phone, multi-phone, syllable or word) and are combined at the word level in the CRF training and decoding processes. A key aspect of our approach is that features are defined at the word level, and are naturally geared to explain long span phenomena such as formant trajectories, duration, and syllable stress patterns. Generalization to unseen words is possible through the use of decomposable consistency features and our framework allows for the joint or separate discriminative training of the acoustic and language models. An initial evaluation of this framework with voice search data from the Bing Mobile (BM) application results in a 2% absolute improvement over an HMM baseline.
Related Papers
- → Effects of Gradual and Sudden Introduction of Perturbations on Adaptive Responses to Formant-Shift and Formant-Clamp Perturbations(2023)8 cited
- → Formant-frequency trajectories as acoustic correlates to speech perception.(2009)2 cited
- → Tracking formants in spectrograms and its application in speaker verification(2012)
- → Identification of Vowel Formants in Short Segments of Speech(1968)
- Research on the discriminating value of different frequency formants in speaker recognition(2009)