MMSE estimation of log-filterbank energies for robust speech recognition

@article{Stark2011MMSEEO,
  title={MMSE estimation of log-filterbank energies for robust speech recognition},
  author={Anthony P. Stark and K. Paliwal},
  journal={Speech Commun.},
  year={2011},
  volume={53},
  pages={403-416}
}
In this paper, we derive a minimum mean square error log-filterbank energy estimator for environment-robust automatic speech recognition. While several such estimators exist within the literature, most involve trade-offs between simplifications of the log-filterbank noise distortion model and analytical tractability. To avoid this limitation, we extend a well known spectral domain noise distortion model for use in the log-filterbank energy domain. To do this, several mathematical… Expand
13 Citations
Computing MMSE Estimates and Residual Uncertainty Directly in the Feature Domain of ASR using STFT Domain Speech Distortion Models
  • 28
  • Highly Influenced
Minimum Mean-Square Error Estimation of Mel-Frequency Cepstral Features–A Theoretically Consistent Approach
  • J. Jensen, Z. Tan
  • Mathematics, Computer Science
  • IEEE/ACM Transactions on Audio, Speech, and Language Processing
  • 2015
  • 17
  • Highly Influenced
  • PDF
On the distribution of Mel-filtered log-spectrum of speech in additive noise
  • 10
  • Highly Influenced
A theoretically consistent method for minimum mean-square error estimation of mel-frequency cepstral features
  • J. Jensen, Z. Tan
  • Computer Science
  • 2014 4th IEEE International Conference on Network Infrastructure and Digital Content
  • 2014
  • 1
MMSE estimation of speech power spectral density under speech presence uncertainty for automatic speech recognition
  • 2
A propagation approach to modelling the joint distributions of clean and corrupted speech in the Mel-Cepstral domain
  • R. Astudillo
  • Computer Science
  • 2013 IEEE Workshop on Automatic Speech Recognition and Understanding
  • 2013
  • 2
Corpus-Based Speech Enhancement With Uncertainty Modeling and Cepstral Smoothing
  • 17
A three layer system for audio-visual quality assessment
  • 3
  • PDF
Velum Movement Detection based on Surface Electromyography for Speech Interface
  • 8
  • PDF
Acoustic Event Detection with MobileNet and 1D-Convolutional Neural Network
...
1
2
...

References

SHOWING 1-10 OF 46 REFERENCES
Robust Speech Recognition Using a Cepstral Minimum-Mean-Square-Error-Motivated Noise Suppressor
  • 68
  • Highly Influential
  • PDF
Minimum Mean-Squared Error Estimation of Mel-Frequency Cepstral Coefficients Using a Novel Distortion Model
  • 31
  • PDF
Energy conditioned spectral estimation for recognition of noisy speech
  • 27
Speech Enhancement Using a-Minimum Mean-Square Error Short-Time Spectral Amplitude Estimator
  • 2,516
  • Highly Influential
  • PDF
Tracking speech-presence uncertainty to improve speech enhancement in non-stationary noise environments
  • D. Malah, R. Cox, A. Accardi
  • Computer Science
  • 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258)
  • 1999
  • 200
Speech enhancement using a minimum mean-square error log-spectral amplitude estimator
  • Y. Ephraim, D. Malah
  • Mathematics, Computer Science
  • IEEE Trans. Acoust. Speech Signal Process.
  • 1985
  • 2,544
  • Highly Influential
Improved noise suppression filter using self-adaptive estimator of probability of speech absence
  • 63
  • PDF
Constrained iterative speech enhancement with application to speech recognition
  • 263
  • PDF
Optimal speech enhancement under signal presence uncertainty using log-spectral amplitude estimator
  • I. Cohen
  • Computer Science, Mathematics
  • IEEE Signal Processing Letters
  • 2002
  • 230
  • PDF
...
1
2
3
4
5
...