Sparse representation features for speech recognition

  title={Sparse representation features for speech recognition},
  author={Tara N. Sainath and Bhuvana Ramabhadran and David Nahamoo and Dimitri Kanevsky and Abhinav Sethy},
In this paper, we explore the use of exemplar-based sparse representations (SRs) to map test features into the linear span of training examples. We show that the frame classification accuracy with these new features is 1.3% higher than a Gaussian Mixture Model (GMM), showing that not only do SRs move test features closer to training, but also move the features closer to the correct class. Given these new SR features, we train up a Hidden Markov Model (HMM) on these features and perform… CONTINUE READING
Highly Cited
This paper has 69 citations. REVIEW CITATIONS

From This Paper

Figures, tables, results, and topics from this paper.

Key Quantitative Results

  • On the TIMIT corpus, we show that applying the SR features on top of our best discriminatively trained system allows for a 0.7% absolute reduction in phonetic error rate (PER), from 19.9% to 19.2%.
  • Furthermore, on a large vocabulary 50 hour broadcast news task, we achieve a reduction in word error rate (WER) of 0.3% absolute, demonstrating the benefit of this method for large vocabulary speech recognition.


Publications citing this paper.
Showing 1-10 of 47 extracted citations

69 Citations

Citations per Year
Semantic Scholar estimates that this publication has 69 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-7 of 7 references

Speech Database Development: Design and Analysis of the Acoustic-Phonetic Corpus

  • L. Lamel, R. Kassel, S. Seneff
  • Proc. of the DARPA Speech Recognition Workshop…
  • 1986
2 Excerpts

Similar Papers

Loading similar papers…