A Hybrid Neural Net System for State-of-the-Art Continuous Speech Recognition

Abstract

Untill recently, state-of-the-art, large-vocabulary, continuous speech recognition (CSR) has employed Hidden Markov Modeling (HMM) to model speech sounds. In an attempt to improve over HMM we developed a hybrid system that integrates HMM technology with neu(cid:173) ral networks. We present the concept of a "Segmental Neural Net" (SNN) for phonetic modeling in CSR. By taking into account all the frames of a phonetic segment simultaneously, the SNN overcomes the well-known conditional-independence limitation of HMMs. In several speaker-independent experiments with the DARPA Resource Manage(cid:173) ment corpus, the hybrid system showed a consistent improvement in performance over the baseline HMM system.

Cite

Text

Zavaliagkos et al. "A Hybrid Neural Net System for State-of-the-Art Continuous Speech Recognition." Neural Information Processing Systems, 1992.

Markdown

[Zavaliagkos et al. "A Hybrid Neural Net System for State-of-the-Art Continuous Speech Recognition." Neural Information Processing Systems, 1992.](https://mlanthology.org/neurips/1992/zavaliagkos1992neurips-hybrid/)

BibTeX

@inproceedings{zavaliagkos1992neurips-hybrid,
  title     = {{A Hybrid Neural Net System for State-of-the-Art Continuous Speech Recognition}},
  author    = {Zavaliagkos, G. and Zhao, Y. and Schwartz, R. and Makhoul, J.},
  booktitle = {Neural Information Processing Systems},
  year      = {1992},
  pages     = {704-711},
  url       = {https://mlanthology.org/neurips/1992/zavaliagkos1992neurips-hybrid/}
}