Recent improvements in the CU Sonic ASR system for noisy speech: the SPINE task

  title={Recent improvements in the CU Sonic ASR system for noisy speech: the SPINE task},
  author={Bryan L. Pellom and Kadri Hacioglu},
In this paper we report on recent improvements in the University of Colorado system for the DARPA/NRL Speech in Noisy Environments (SPINE) task. In particular, we describe our efforts on improving acoustic and language modeling for the task and investigate methods for unsupervised speaker and environment adaptation from limited data. We show that the MAPLR adaptation method outperforms single and multiple regression class MLLR on the SPINE task. Our current SPINE system uses the Sonic speech… CONTINUE READING
Highly Cited
This paper has 103 citations. REVIEW CITATIONS

From This Paper

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

Key Quantitative Results

  • This system is shown to have a word error rate of 31.5% on the SPINE-2 evaluation data. These improvements amount to a 16% reduction in relative word error rate compared to our previous SPINE-2 system fielded in the Nov. 2001 DARPA/NRL evaluation.


Publications citing this paper.
Showing 1-10 of 56 extracted citations

103 Citations

Citations per Year
Semantic Scholar estimates that this publication has 103 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 15 references

Sonic: The University of Colorado Continuous Speech Recognizer

  • B. Pellom
  • Technical Report TR-CSLR-2001-01, CSLR…
  • 2001
Highly Influential
9 Excerpts

Speech in Noisy Environments (SPINE) Adds News Dimension to Speech Recognition R & D

  • T. Crystal, A. Schmidt-Nelson, E. Marsh
  • Proc. HLT Conf., San Diego, March 2002.
  • 2002
1 Excerpt

Similar Papers

Loading similar papers…