Skip to main content

Research Repository

Advanced Search

All Outputs (47)

Machine learning and DSP algorithms for screening of possible osteoporosis using electronic stethoscopes (2018)
Presentation / Conference Contribution

Osteoporosis is a prevalent but asymptomatic condition that affects a large population of the elderly, resulting in a high risk of fracture. Several methods have been developed and are available in general hospitals to indirectly assess the bone qual... Read More about Machine learning and DSP algorithms for screening of possible osteoporosis using electronic stethoscopes.

Detection of Osteoporosis from Percussion Responses Using an Electronic Stethoscope and Machine Learning (2018)
Journal Article

Osteoporosis is an asymptomatic bone condition that affects a large proportion of the elderly population around the world, resulting in increased bone fragility and increased risk of fracture. Previous studies had shown that the vibroacoustic respons... Read More about Detection of Osteoporosis from Percussion Responses Using an Electronic Stethoscope and Machine Learning.

Robust speaker recognition in reverberant condition : toward greater biometric security (2018)
Thesis
Al-Karawi, K. (in press). Robust speaker recognition in reverberant condition : toward greater biometric security. (Thesis). University of Salford

Automatic speaker recognition systems have developed into an increasingly relevant technology for security applications in modern times. The primary challenge for automatic speaker recognition is to deal with the variability of the environments and c... Read More about Robust speaker recognition in reverberant condition : toward greater biometric security.

Mitigating wind induced noise in outdoor microphone signals using a singular spectral subspace method (2018)
Journal Article
Eldwaik, O., & Li, F. (2018). Mitigating wind induced noise in outdoor microphone signals using a singular spectral subspace method. Technologies, 6(1), https://doi.org/10.3390/technologies6010019

Wind induced noise is one of the major concerns of outdoor acoustic signal acquisition. It affects many field measurement and audio recording scenarios. Filtering such noise is known to be
difficult due to its broadband and time varying nature. In t... Read More about Mitigating wind induced noise in outdoor microphone signals using a singular spectral subspace method.

Microphone wind noise reduction using singular spectrum analysis techniques (2017)
Presentation / Conference
Eldwaik, O., & Li, F. (2017, November). Microphone wind noise reduction using singular spectrum analysis techniques. Presented at 33nd Annual Conference And Exhibition. Reproduced Sound 2017 : Sound Quality By Design, Nottingham, UK

Wind noise is a known problem that contaminates microphone signals in many field measurement and audio recording scenarios. A recently completed EPSRC project has led to the development of a tool to detect such noise; this paper takes a step further... Read More about Microphone wind noise reduction using singular spectrum analysis techniques.

Mitigating wind noise in outdoor microphone signals using a singular spectral subspace method (2017)
Presentation / Conference
Eldwaik, O., & Li, F. (2017, August). Mitigating wind noise in outdoor microphone signals using a singular spectral subspace method. Presented at IEEE, Seventh International Conference on Innovative Computing Technology (INTECH 2107), Luton, UK

Wind noise is one of the major concerns of outdoor microphone signal acquisition. Filtering and removal of wind noise are known to be difficult due to its broadband and time varying nature. This paper proposes the use of singular spectrum analysis to... Read More about Mitigating wind noise in outdoor microphone signals using a singular spectral subspace method.

Robust speaker verification in reverberant conditions using estimated acoustic parameters : a maximum likelihood estimation and training on the fly approach (2017)
Presentation / Conference
Yousif, K., & Li, F. (2017, August). Robust speaker verification in reverberant conditions using estimated acoustic parameters : a maximum likelihood estimation and training on the fly approach. Presented at 7th International Conference on Innovative Computing Technology (INTECH 2017), Luton, UK

Speaker recognition has been developed into a relatively mature state over the past few decades through continuous research and development work. Existing methods typically use the robust features extracted from noise and reverberation free speech si... Read More about Robust speaker verification in reverberant conditions using estimated acoustic parameters : a maximum likelihood estimation and training on the fly approach.

Training "on the fly" to improve the performance of speaker recognition in noisy environments (2017)
Book Chapter
Al-Noori, A., Duncan, P., & Li, F. (2017). Training "on the fly" to improve the performance of speaker recognition in noisy environments. In Proceedings: 2017 AES International Conference on Audio Forensics. Audio Engineering Society

Reliability of Speaker Recognition (SR) is crucial for critical applications, especially in adverse acoustic
conditions. Ambient noises and their variations represent a significant challenge for such applications. In this
paper, a new technique is... Read More about Training "on the fly" to improve the performance of speaker recognition in noisy environments.

Robustness of speaker recognition from noisy speech samples and mismatched languages (2016)
Presentation / Conference
Al-Noori, A., Li, F., & Duncan, P. (2016, June). Robustness of speaker recognition from noisy speech samples and mismatched languages. Presented at 140th Convention-AES, Paris

Speaker recognition systems can typically attain high performance in ideal conditions. However, significant degradations in accuracy are found in channel-mismatched scenarios. Non-stationary environmental noises and their variations are listed at the... Read More about Robustness of speaker recognition from noisy speech samples and mismatched languages.

Audio content feature selection and classification : a random forests and decision tree approach (2015)
Presentation / Conference
AI-Maathidi, M., & Li, F. (2015, December). Audio content feature selection and classification : a random forests and decision tree approach. Presented at IEEE International Conference on Progress in Informatics and Computing (PIC), Nanjing, China

Content information can be extracted from soundtracks of multimedia files. A good audio classifier as a preprocessor
is crucial in such applications. Efforts have been made
to develop effective and efficient audio content classifiers in
which feat... Read More about Audio content feature selection and classification : a random forests and decision tree approach.

Automatic Speaker Recognition System in Adverse Conditions — Implication of Noise and Reverberation on System Performance (2015)
Journal Article
A. Al-Karawi, K., H. Al-Noori, A., Li, F., & Ritchings, T. (2015). Automatic Speaker Recognition System in Adverse Conditions — Implication of Noise and Reverberation on System Performance. International journal of information and electronics engineering (Singapore : Online), 5(6), 423-427. https://doi.org/10.7763/IJIEE.2015.V5.571

Speaker recognition has been developed and evolved over the past few decades into a supposedly mature technique. Existing methods typically utilize robust features
extracted from clean speech. In real-world applications,
especially security and for... Read More about Automatic Speaker Recognition System in Adverse Conditions — Implication of Noise and Reverberation on System Performance.

Perceived audio quality of sounds degraded by non-linear distortions and single-ended assessment using HASQI (2015)
Journal Article
assessment using HASQI. Journal of the Audio Engineering Society, 63(9), 698-712. https://doi.org/10.17743/jaes.2015.0068

For field recordings and user generated content recorded on phones, tablets, and other mobile
devices nonlinear distortions caused by clipping and limiting at pre-amplification stages, and
dynamic range control (DRC) are common causes of poor audio... Read More about Perceived audio quality of sounds degraded by non-linear distortions and single-ended assessment using HASQI.

Audio content analysis in the presence of overlapped classes : a non-exclusive segmentation approach to mitigate information losses (2015)
Presentation / Conference
Mohammed, D., Duncan, P., & Li, F. (2015, August). Audio content analysis in the presence of overlapped classes : a non-exclusive segmentation approach to mitigate information losses. Presented at Global Summit and Expo on Multimedia & Applications, Birmingham, UK

Soundtracks of multimedia files are information rich, from which much content-related metadata can be extracted. There is a pressing demand for automated classification, identification and information mining of audio content. A segment of the audio s... Read More about Audio content analysis in the presence of overlapped classes : a non-exclusive segmentation approach to mitigate information losses.

Improving headphone user experience in ubiquitous multimedia content consumption : a universal cross-feed filter (2015)
Presentation / Conference
Li, F. (2015, June). Improving headphone user experience in ubiquitous multimedia content consumption : a universal cross-feed filter. Presented at IEEE BMSB 2015, Ghent, Belgium

High performance audio and video codecs and ever
increasing bandwidths of data communications networks have
enabled multi-platform delivery of high definition media content
via transmission channels such as terrestrial broadcast,
broadband IP net... Read More about Improving headphone user experience in ubiquitous multimedia content consumption : a universal cross-feed filter.

Independent Component Analysis Methods to Improve Electrocardiogram Patterns Recognition in the Presence of Non-Trivial Artifacts (2015)
Journal Article
Sarfraz, M., Li, F., & Khan, A. (2015). Independent Component Analysis Methods to Improve Electrocardiogram Patterns Recognition in the Presence of Non-Trivial Artifacts. Journal of medical and bioengineering, 4(3), 221-226. https://doi.org/10.12720/jomb.4.3.221-226

Electrocardiogram (ECG) signals are affected by various kinds of noise and artifacts that may impede correct recognition by automated monitoring or diagnosis systems. Independent component analysis (ICA) is considered as a new technique suitable for... Read More about Independent Component Analysis Methods to Improve Electrocardiogram Patterns Recognition in the Presence of Non-Trivial Artifacts.

Improving robustness of speaker recognition in noisy and reverberant conditions via training (2015)
Book Chapter
Al-Noori, A., Al-Karawi, K., & Li, F. (2015). Improving robustness of speaker recognition in noisy and reverberant conditions via training. In 2015 European Intelligence and Security Informatics Conference (180-180). IEEE. https://doi.org/10.1109/EISIC.2015.20

Speaker recognition can be used as a security means to authenticate the speaker or as a forensic tool to determine who is likely to be the talker. For such critical applications, robustness or reliability of the system is crucial. In spite of the dev... Read More about Improving robustness of speaker recognition in noisy and reverberant conditions via training.