Skip to main content

Research Repository

Advanced Search

All Outputs (47)

Extracting room reverberation time from speech using artificial neural networks (2001)
Journal Article
Cox, T., Li, F., & Darlington, P. (2001). Extracting room reverberation time from speech using artificial neural networks. Journal of the Audio Engineering Society, 49(4), 219-230

A novel method to extract the reverberation time from reverberated speech utterances is presented. In this study, speech utterances are restricted to pronounced digits; uncontrolled discourse is not considered. The reverberation times considered are... Read More about Extracting room reverberation time from speech using artificial neural networks.

Speech intelligibility of VoIP to PSTN interworking - a key index for the QoS
Presentation / Conference
Li, F. Speech intelligibility of VoIP to PSTN interworking - a key index for the QoS. Presented at Telecommunications Quality of Services: The Business of Success, 2004. QoS 2004. IEE

Intelligibility is an important concern of speech transmission channels. The paper addresses speech intelligibility issues in the VoIP to PSTN interworking context, discusses the complexity of quantifying speech intelligibility, and advocates speech... Read More about Speech intelligibility of VoIP to PSTN interworking - a key index for the QoS.

EMC of power suppliers for telecommunications by design - a computational approach
Presentation / Conference
Li, F. EMC of power suppliers for telecommunications by design - a computational approach. Presented at Telecommunications Energy Conference, 2001. INTELEC 2001. Twenty-Third International

This paper proposes a simplified computational method for estimating radiated electromagnetic interference (EMI) from power supply units (PSUs) and then inversely applies it to design problems. Practical considerations are centered on PSUs used in mo... Read More about EMC of power suppliers for telecommunications by design - a computational approach.

A system for semantic information extraction from mixed soundtracks deploying MARSYAS framework
Book Chapter
Mohammed, D., Duncan, P., Al-Maathidi, M., & Li, F. A system for semantic information extraction from mixed soundtracks deploying MARSYAS framework. In 2015 IEEE 13th International Conference on Industrial Informatics (INDIN) (1084-1089). IEEE. https://doi.org/10.1109/INDIN.2015.7281886

Ever increasing volumes of media content and the desire to extract information from media archives motivate the studies into semantic audio information mining. Much research in this filed concerns development of bespoke systems, in which sound tracks... Read More about A system for semantic information extraction from mixed soundtracks deploying MARSYAS framework.

Audio information extraction from arbitrary sound recordings
Presentation / Conference
Duncan, P., Mohammed, D., & Li, F. Audio information extraction from arbitrary sound recordings. Presented at 22nd International Congress on Sound and Vibration (ICSV22), Florence, Italy

Numerous archives of entertainment soundtracks and other recordings such as environmental noise samples have imposed a big data challenge in audio related industries. This necessitates the use of machine audition and retrieval tools to extract semant... Read More about Audio information extraction from arbitrary sound recordings.

Estimation of intelligibility from received arbitrary speech signals with support vector machine
Presentation / Conference
Li, F. Estimation of intelligibility from received arbitrary speech signals with support vector machine. Presented at 2005 International Conference on Machine Learning and Cybernetics, Guangzhou, China

Intelligibility, a vital concern of a speech transmission channel, is quantified using speech transmission index (STI). The standard STI method relies on noisy test signals and thus hinders in-use measurements. Alternative methods to accurately estim... Read More about Estimation of intelligibility from received arbitrary speech signals with support vector machine.