Christine Evers will be giving a keynote speech at UK Speech 2017 in Cambridge on “Acoustic Scene Mapping for Robot Audition”.

The slides for Christine Evers’s keynote speech on “Bayesian Learning for Robot Audition” at HSCMA 2017 are now online on the website of the IEEE Audio and Acoustic Signal Processing Technical Committee.

Israel Dejene Gebru from the Perception Group at INRIA and his co-authors, Christine Evers, Patrick Naylor, and Radu Horaud, received the best paper award at the IEEE Fifth Joint Workshop on Hands-free Speech Communication and Microphone Arrays, San Francisco, USA, 1-3 March 2017, for their paper on “Audio-visual Tracking by Density Approximation in a Sequential Bayesian Filtering Framework”.

Best Paper Award HSCMA 2017

We have now published the bias, mean-squared-error (MSE), and Pearson correlation coefficient (CC) in each frequency band for the four frequency-dependent algorithm submissions to the ACE Challenge.

We have updated Figs. 25-37 and 52-88 in the ACE Challenge Results Technical Report to show the CC, and added tables 22-33 and 46-84 to show the bias, MSE, and CC numerically. We hope that this will help you with your research.

If you are using data from the ACE Challenge Results Technical Report, please cite it alongside the citation to the ACE journal paper.

Eaton, James; Gaubitch, Nikolay D.; Moore, Alastair H.; Naylor, Patrick A.

Acoustic Characterization of Environments (ACE) Challenge Results Technical Report (revised) (Technical Report)

Imperial College London 2017.

(Abstract | Links | BibTeX)

We are looking forward to presenting the following papers and keynote at HSCMA in San Francisco 1-3 March 2017.

Dionelis, Nikolaos; Brookes, Mike

Modulation-Domain Speech Enhancement using a Kalman Filter with a Bayesian Update of Speech and Noise in the Log-Spectral Domain (Inproceeding)

Proc. Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA), San Francisco, CA, USA, 2017.

(Abstract | BibTeX)

Eaton, J.; Javed, Hamza A.; Naylor, Patrick A.

Estimation of the perceived level of reverberation using non-intrusive single-channel variance of decay rates (Inproceeding)

Proc. Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA), San Francisco, CA, USA, 2017.

(Abstract | Links | BibTeX)

Evers, C.; Rafaely, B.; Naylor, P. A.

Speaker Tracking in Reverberant Environments using Multiple Directions of Arrival (Inproceeding)

HSCMA, 2017.

(BibTeX)

Gebru, I. D.; Evers, C.; Naylor, P. A.; Horaud, R.

Audio-Visual Tracking by Density Approximation in a Sequential Bayesian Filtering Framework (Inproceeding)

HSCMA, 2017.

(BibTeX)

Evers, C.

Keynote Speech on Bayesian Learning for Robot Audition (Presentation)

01.03.2017.

(Abstract | BibTeX)

Hafezi, Sina; Moore, Alastair H.; Naylor, Patrick A.

Multi-source Estimation Consistency for Improved Multiple Direction-of-Arrival estimation (Inproceeding)

Proc. Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA), San Francisco, CA, USA, 2017.

(BibTeX)

Pablo Peso, a PhD student in the DREAMS research programme has received the DREAMS Best Paper Award (Marie Skłodowska-Curie Research and Innovation, Innovative Training Network `DREAMS’) for his paper entitled “A single-channel non-intrusive C50 estimator correlated with speech recognition performance”, IEEE Transactions on Audio, Speech and Language Processing, Vol. 24, April 2016. The paper is co-authored with: D. Sharma, J. Lainez, D. Barreda, T. van Waterschoot, and P.A. Naylor. [PDF]

We are delighted to announce that Dr Christine Evers was awarded an EPSRC Fellowship on “Acoustic Signal Processing and Scene Analysis for Socially Assistive Robots”, starting on 1 January 2017.

Christine’s research will focus on acoustic Simultaneous Localization and Mapping (aSLAM), source tracking, and blind speech enhancement, aiming to provide robots and autonomous systems with a situational awareness of the acoustic environment. Grant details can be found at: http://gow.epsrc.ac.uk/NGBOViewGrant.aspx?GrantRef=EP/P001017/1

Stay tuned for the following papers to be presented at ICASSP 2017 in March.

Merry Christmas and happy holidays!

 

  • Costas Yiallourides, Victoria Manning-Eid, Alastair H. Moore, Patrick A. Naylor (2017): A Dynamic Programming Approach for Automatic Stride Detection and Segmentation in Acoustic Emission from the Knee. In: Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2017.
  • Constantinos Papayiannis, Christine Evers, Patrick A. Naylor (2017): Discriminative Feature Domains for Reverberant Acoustic Environments. In: Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2017.
  • Sina Hafezi, Alastair H. Moore, Patrick A. Naylor (2017): Multiple Source Localization using Estimation Consistency in the Time-Frequency Domain. In: Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2017.
  • Christine Evers, Yuval Dorfan, Sharon Gannot,, Patrick A. Naylor (2017): Source Tracking using Moving Microphone Arrays for Robot Audition. In: Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), ICASSP, 2017.
  • H. A. Javed, B. Cauchi, S. Doclo, P. A. Naylor, S. Goetze (2017): Measuring, Modelling and Predicting Perceived Reverberation. In: Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2017.
  • Alastair H. Moore, Mike Brookes, Patrick A. Naylor (2017): Robust spherical harmonic domain interpolation of spatially sampled array manifolds. In: Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2017.
  • Wei Xue, Mike Brookes, Patrick A. Naylor (2017): Frequency-Domain Under-Modelled Blind System Identification Based on Cross Power Spectrum and Sparsity Regularization. In: Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2017.
  • Leo Lightburn, Enzo De Sena, Alastair Moore, Patrick A. Naylor, Mike Brookes (2017): Improving the Perceptual Quality of Ideal Binary Masked Speech. In: Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2017.

 

It’s been a busy summer.

Congratulations to Richard Stanton, who passed his PhD Viva in August. Then in September it was conference season with the following papers being presented by members of our group.

EUSIPCO

Dionelis, Nikolaos; Brookes, Mike

Active speech level estimation in noisy signals with quadrature noise suppression (Inproceeding)

Proc. European Signal Processing Conf. (EUSIPCO), 2016.

(Links | BibTeX)

Gannot, Yuval Dorfan, Christine Evers, Sharon; Naylor, Patrick A.

Speaker Localization with Moving Microphone Arrays (Inproceeding)

EUSIPCO, 2016.

(BibTeX)

Evers, C.; Moore, A. H.; Naylor, P. A.

Localization of Moving Microphone Arrays from Moving Sound Sources for Robot Audition (Inproceeding)

EUSIPCO, 2016.

(BibTeX)

Hafezi, S.; Moore, A. H.; Naylor, P. A.

Multiple source localization in the spherical harmonic domain using augmented intensity vectors based on grid search (Inproceeding)

Proc. European Signal Processing Conf. (EUSIPCO), Budapest, Hungary, 2016.

(Links | BibTeX)

Moore, Alastair H.; Evers, Christine; Naylor, Patrick A.

2D direction of arrival estimation of multiple moving sources using a spherical microphone array (Inproceeding)

Proc. European Signal Processing Conf. (EUSIPCO), 2016.

(Links | BibTeX)

Xue, Wei; Brookes, Mike; Naylor, Patrick A.

Cross-Correlation Based Under-Modelled Multichannel Blind Acoustic System Identification with Sparsity Regularization (Inproceeding)

Proc. European Signal Processing Conf. (EUSIPCO), 2016.

(BibTeX)

IWAENC

Javed, Hamza A.; Moore, Alastair H.; Naylor, Patrick A.

Spherical harmonic rake receivers for dereverberation (Inproceeding)

Proc. Intl. Workshop on Acoustic Signal Enhancement (IWAENC), 2016.

(BibTeX)

Moore, Alastair H.; Naylor, Patrick A.

Linear prediction based dereverberation for spherical microphone arrays (Inproceeding)

Proc. Intl. Workshop on Acoustic Signal Enhancement (IWAENC), 2016.

(Links | BibTeX)

Xue, Wei; Brookes, Mike; Naylor, Patrick A.

Under-Modelled Blind System Identification for Time Delay Estimation in Reverberant Environments (Inproceeding)

Proc. Intl. Workshop on Acoustic Signal Enhancement (IWAENC), 2016.

(BibTeX)

Clement passed his PhD viva last week. Many congratulations!

« Older entries