A hybrid SVM/HMM acoustic modeling approach to automatic speech recognition

@inproceedings{Stadermann2004AHS,
  title={A hybrid SVM/HMM acoustic modeling approach to automatic speech recognition},
  author={Jan Stadermann and Gerhard Rigoll},
  booktitle={INTERSPEECH},
  year={2004}
}
Acoustic models based on a NN/HMM framework have been used successfully on various recognition tasks for continuous speech recognition. Recently tied-posteriors have been introduced within this context. Here, we present an approach combining SVMs and HMMs using the tied-posteriors idea. One set of SVMs calculates class posterior probabilities and shares these probabilities among all HMMs. The number of SVMs is varied as well as the input context and the amount of training data. Applying a first… CONTINUE READING
Highly Cited
This paper has 28 citations. REVIEW CITATIONS