The Microsoft 2017 Conversational Speech Recognition System

@article{Xiong2017TheM2,
  title={The Microsoft 2017 Conversational Speech Recognition System},
  author={W. Xiong and L. Wu and Fil Alleva and Jasha Droppo and Xuedong Huang and Andreas Stolcke},
  journal={2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2017},
  pages={5934-5938}
}
We describe the latest version of Microsoft's conversational speech recognition system for the Switchboard and CallHome domains. [...] Key ResultThe resulting system yields a 5.1% word error rate on the NIST 2000 Switchboard test set, and 9.8% on the CallHome subset. Expand Abstract

Citations

Publications citing this paper.
SHOWING 1-10 OF 137 CITATIONS

Language modeling with highway LSTM

  • 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
  • 2017
VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Session-level Language Modeling for Conversational Speech

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND

Deep Neural Networks for Sound Event Detection

VIEW 7 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

An Investigation of Word Embeddings with Deep Bidirectional LSTM for Sentence Unit Detection in Automatic Speech Transcription

  • 2018 International Conference on Asian Language Processing (IALP)
  • 2018
VIEW 2 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

The Marchex 2018 English Conversational Telephone Speech Recognition System

VIEW 4 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2017
2019

CITATION STATISTICS

  • 7 Highly Influenced Citations

  • Averaged 46 Citations per year from 2017 through 2019

  • 105% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 58 REFERENCES