Efficient On-The-Fly Hypothesis Rescoring in a Hybrid GPU/CPU-based Large Vocabulary Continuous Speech Recognition Engine

@inproceedings{Kim2012EfficientOH,
  title={Efficient On-The-Fly Hypothesis Rescoring in a Hybrid GPU/CPU-based Large Vocabulary Continuous Speech Recognition Engine},
  author={Jungsuk Kim and Jike Chong and Ian R. Lane},
  booktitle={INTERSPEECH},
  year={2012}
}
Effectively exploiting the resources available on modern multicore and manycore processors for tasks such as large vocabulary continuous speech recognition (LVCSR) is far from trivial. While prior works have demonstrated the effectiveness of manycore graphic processing units (GPU) for high-throughput, limited vocabulary speech recognition, they are unsuitable for recognition with large acoustic and language models due to the limited 1-6GB of memory on GPUs. To overcome this limitation, we… CONTINUE READING
Highly Cited
This paper has 18 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 14 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 12 references

CMU/InterACT Arabic Speech Recognition System for GALE

  • U. Nallasamy, I. Lane, +4 authors T. Schultz
  • Handbook of Natural Language Processing and…
  • 2011
Highly Influential
5 Excerpts

CMU/InterACT Mandarin Speech Recognition System for GALE

  • R. Hsiao, M. Fuhs, Q.J.Y. Tam, I. Lane, T. Schultz
  • Handbook of Natural Language Processing and…
  • 2011
Highly Influential
6 Excerpts

Similar Papers

Loading similar papers…