With the increase in the computational complexity of recent computers, audio-visual speech recognition (AVSR) became an attractive research topic that can lead to a robust solution for speech recognition in noisy environments. In the audio visual continuous speech recognition system presented in this paper, the audio and visual observation sequences are integrated using a coupled hidden Markov ...

Vehicle digital forensics includes the process of collecting and analysing data stored in vehicles to find evidence related traffic accidents or crime scenes. Through this process, we can reconstruct events by recognizing various information such as driver behaviour, driving patterns, vehicle destinations, smartphones connected a vehicle. Recently, many forensic studies have been conducted, but...

We consider wearable computing applications which rely on audio as a primary medium of the interface. This paper surveys a range of interaction techniques which may be applied to the design of wearable audio computers (WACs). A summary of several speech and audio processing technologies which can be used in the interface of WACs are reviewed. We present several usage scenarios and focus on two ...

New application spaces and artistic forms can emerge when users are freed from constraints. In the general case of human-computer interfaces, users are often confined to a fixed location, severely limiting mobility. To overcome this constraint in the context of musical interaction, we present a system to manage large-scale collaborative mobile audio environments, driven by user movement. Multip...

As the multimedia content of the Web increases techniques to automatically classify this content become more important. In this paper we present a system to classify audio les collected from the Web. The system classi es any audio le as belonging to one of three categories: `speech', `music' and `other'. To classify the audio les, we use the technique of Fisher kernels. The technique as propose...

In present stereo audio system is a most popular audio system for different purposes. Now a day’s stereo system is commonly used in communication and other purposes. Moreover Normalized Least Mean Square (NLMS) based adaptive filtering is an effective filtering process in case of communication and other applications. However adaptive filtering is an adaptive filter process to cancel out the noi...

We report on an audio retrieval system which lets Internet users efficiently access a large audio database containing recordings of the proceedings of the United States House of Representatives. The audio has been temporally aligned to text transcripts of the proceedings (which are manually generated by the U.S. Government) using a novel method based on speaker identification. Speaker sequence ...