Abstract
The speech enhancement research presented here was motivated by several factors. Firstly, the development in recent years of audio-only hearing aids that utilise sophisticated decision rules to determine the appropriate level of speech processing served as an inspiration. A second motivational factor was the exploitation of the established cognitive relationship between audio and visual elements of speech to produce multimodal speech filtering systems. Another motivation was the desire to utilise audiovisual speech filtering to extend the concept of audio-only speech processing to become multimodal, from the perspective of potential application to hearing aids. Based on these motivations, the goal of the work presented in this book was primarily to develop a flexible two-stage multimodal speech enhancement system, working towards the development of a cognitively inspired fuzzy logic based speech enhancement framework that is autonomous, adaptive, and context aware. The novel proof of concept framework presented in this book makes use of audio-only beamforming, visually derived Wiener filtering, state-of-the-art lip tracking with Viola-Jones ROI detection, and a fuzzy logic controller, to present a novel speech enhancement framework. This chapter presents some conclusions and future work.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
S. Calinon, F. Guenter, A. Billard, On learning, representing, and generalizing a task in a humanoid robot. IEEE Trans. Syst. Man Cybern. Part B 37(2), 286–298 (2007)
I. Almajai, B. Milner, Effective visually-derived Wiener filtering for audio-visual speech processing, in Proceeding Interspeech. (Brighton, UK, 2009)
W. Maass, T. Natschläger, H. Markram, Real-time computing without stable states: a new framework for neural computation based on perturbations. Neural Comput. 14(11), 2531–2560 (2002)
S. Scherer, M. Glodek, F. Schwenker, N. Campbell, G. Palm, Spotting laughter in natural multiparty conversations: a comparison of automatic online and offline approaches using audiovisual data. ACM Trans. Interact. Intell. Syst. (TiiS) 2(1), 4 (2012)
M. Newton, L. Smith, A neurally inspired musical instrument classification system based upon the sound onset. J. Acoust. Soc. Am. 6, 4785–4798 (2012)
W. Maass, Networks of spiking neurons: the third generation of neural network models. Neural Netw. 10(9), 1659–1671 (1997)
L.S. Smith, D.S. Fraser, Robust sound onset detection using leaky integrate-and-fire neurons with depressing synapses. IEEE Trans. Neural Netw. 15(5), 1125–1134 (2004)
M. Sargin, Y. Yemez, E. Erzin, A. Tekalp, Audiovisual synchronization and fusion using canonical correlation analysis. IEEE Trans. Multimed. 9(7), 1396–1403 (2007)
A. Abel, A. Hussain, Q. Nguyen, F. Ringeval, M. Chetouani, M. Milgram, Maximising audiovisual correlation with automatic lip tracking and vowel based segmentation, in Proceeding of Biometric ID Management and Multimodal Communication: Joint COST 2101 and 2102 International Conference, \(BioID\_MultiComm\) 2009, Madrid, Spain, 16–18 September 2009, vol. 5707, (Springer, 2009) pp. 65–72
I. Almajai, B. Milner, Enhancing audio speech using visual speech features, in Proceedings of the Interspeech (Brighton, 2009)
K. Chung, Challenges and recent developments in hearing aids. Part i. Speech understanding in noise, microphone technologies and noise reduction algorithms. Trends Amplif. 8(3), 83–124 (2004)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2015 The Author(s)
About this chapter
Cite this chapter
Abel, A., Hussain, A. (2015). Potential Future Research Directions. In: Cognitively Inspired Audiovisual Speech Filtering. SpringerBriefs in Cognitive Computation, vol 5. Springer, Cham. https://doi.org/10.1007/978-3-319-13509-0_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-13509-0_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-13508-3
Online ISBN: 978-3-319-13509-0
eBook Packages: Biomedical and Life SciencesBiomedical and Life Sciences (R0)