An Overview of Noise-Robust Automatic Speech Recognition

@article{Li2014AnOO,
  title={An Overview of Noise-Robust Automatic Speech Recognition},
  author={Jinyu Li and Li Deng and Yifan Gong and Reinhold H{\"a}b-Umbach},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  year={2014},
  volume={22},
  pages={745-777}
}
New waves of consumer-centric applications, such as voice search and voice interaction with mobile devices and home entertainment systems, increasingly require automatic speech recognition (ASR) to be robust to the full range of real-world noise and other acoustic distorting conditions. Despite its practical importance, however, the inherent links between and distinctions among the myriad of methods for noise-robust ASR have yet to be carefully studied in order to advance the field further. To… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 234 CITATIONS

Deep Neural Network-based Speech Separation Combining with MVDR Beamformer for Automatic Speech Recognition System

  • 2019 IEEE International Conference on Consumer Electronics (ICCE)
  • 2019
VIEW 8 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Single Channel Target Speaker Extraction and Recognition with Speaker Beam

  • 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2018
VIEW 8 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Statistical Language and Speech Processing

Yuzuru Tanaka, LNAI Founding
  • Lecture Notes in Computer Science
  • 2018
VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Unsupervised help-trained LS-SVR-based segmentation in speaker diarization system

  • Multimedia Tools and Applications
  • 2018
VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

ACCURACY IN THE PRESENCE OF BACKGROUND NOISE

VIEW 5 EXCERPTS
CITES BACKGROUND & RESULTS
HIGHLY INFLUENCED

Feature mapping using deep belief networks for robust speech recognition

Mojtaba Gholamipoor, Babak Nasersharif
  • 2017
VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Raw waveform-based speech enhancement by fully convolutional networks

  • 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
  • 2017
VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2012
2019

CITATION STATISTICS

  • 29 Highly Influenced Citations

  • Averaged 45 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 39 REFERENCES

A variational perspective on noise-robust speech recognition

  • 2011 IEEE Workshop on Automatic Speech Recognition & Understanding
  • 2011
VIEW 13 EXCERPTS
HIGHLY INFLUENTIAL

Predictive linear transforms for noise robust speech recognition

  • 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)
  • 2007
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Cluster adaptive training of hidden Markov models

  • IEEE Trans. Speech and Audio Processing
  • 2000
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Tandem connectionist feature extraction for conventional HMM systems

  • 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)
  • 2000
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

A compact model for speaker-adaptive training

  • Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96
  • 1996
VIEW 17 EXCERPTS
HIGHLY INFLUENTIAL

Speech recognition in noisy environments

VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Environment normalization for robust speech recognition using direct cepstral comparison

  • Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing
  • 1994
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL