Classification and Ranking Approaches to Discriminative Language Modeling for ASR

@article{Dikici2013ClassificationAR,
  title={Classification and Ranking Approaches to Discriminative Language Modeling for ASR},
  author={Erinç Dikici and Murat Semerci and Murat Saraclar and Ethem Alpaydin},
  journal={IEEE Transactions on Audio, Speech, and Language Processing},
  year={2013},
  volume={21},
  pages={291-300}
}
Discriminative language modeling (DLM) is a feature-based approach that is used as an error-correcting step after hypothesis generation in automatic speech recognition (ASR). We formulate this both as a classification and a ranking problem and employ the perceptron, the margin infused relaxed algorithm (MIRA) and the support vector machine (SVM). To decrease training complexity, we try count-based thresholding for feature selection and data sampling from the list of hypotheses. On a Turkish… CONTINUE READING
Highly Cited
This paper has 27 citations. REVIEW CITATIONS
16 Citations
25 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 16 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 25 references

A library for large linear classi fi cation

  • K.-W. Chang, C.-J. Hsieh, X.-R. Wang, C.-J. Lin
  • J . Mach . Learn . Res .
  • 2008

D3.2 Learning methods for discriminative language models

  • M. Vuorinen, M. Kaariainen, J. Rousu, Z. Wang, P. Mahe, C. Cancedda
  • SMART Project Rep., Jun. 2008.
  • 2008
1 Excerpt

Similar Papers

Loading similar papers…