In this study, we employ skip connections into a deep recurrent neural network for modeling basic dance steps using audio as input. Our model consists of two blocks, one encodes the audio input sequences, and another generates the motion. The encoder uses a configuration called convolutional, long short-term memory deep neural network (CLDNN) which handle the power features of audio. Furthermor...

This paper describes the audio component of a virtual reality system that uses remote sensing to free the user from body-mounted tracking equipment. Position information is obtained from a camera and used to constrain a beam-forming microphone array, for fareld speech input, and a two-speaker transaural audio system for rendering 3D audio. 1 Vision Steered Beam-Forming 1.

This work explores the use of audio recognition techniques to evaluate how well users brush their teeth using only audio data collected from smartphones. We investigate two main approaches: a two-tiered approach that first performs activity recognition on the audio data and then uses the output of activity recognition to build a regression model for skill assessment, and an approach that uses d...

We introduce the notion of musical gestures as time varying measurements which identify the audio input stream’s musical skeleton without attempting to implement any involved model of musical understanding. Living comfortably at an intermediate level of abstraction between wave forms and music transcriptions, these musical gestures are used to control the behavior of an audio processing module....

An audio descriptor describes the information of an audio signal in a compact and precise representation. There are various standards available to extract the audio information in various ways to be used for particular applications such as, speaker recognition, musical instrument identification, singer identification, multimedia database indexing, genre detection and so on. There are various au...

With the increase in the bandwidth & the transmission speed over the internet, transmission of multimedia objects like video, audio, images has become an easier work. In this paper we provide an approach that can be useful for transmission of video objects over the internet without much fuzz. The approach provides a ontology based framework that is used to establish an automatic deployment of v...

A new patented balanced input circuit emulates the extremely high common-mode input impedances which give a quality audio transformer its hum and buzz rejecting advantage in real-world audio systems, where driving source impedances are rarely perfectly balanced. Compared to traditional "active balanced" circuits, the new circuit can produce CMRR improvements up to 80 dB but is only slightly mor...

This paper presents a reconfigurable sigma-delta audio Digital-to-Analog Converter (DAC) which is suitable for embedded FPGA applications. The Sigma-Delta Modulator (SDM) design can be configured as a 3rd or 5th order SDM and allows different input word lengths. Different input sampling rates are also entertained by employing a programmable interpolator. The DAC accepts 16-/18-/20-/24-bit PCM d...