In this paper, we propose a parallel Convolutional Neural Network architecture for the task of classifying acoustic scenes and urban sound scapes. A popular choice for input to a Convolutional Neural Network in audio classification problems are Mel-transformed spectrograms. We, however, show in this paper that a ConstantQ-transformed input improves results. Furthermore, we evaluated critical pa...

In deep neural networks with convolutional layers, each layer typically has fixed-size/single-resolution receptive field (RF). Convolutional layers with a large RF capture global information from the input features, while layers with small RF size capture local details with high resolution from the input features. In this work, we introduce novel deep multi-resolution fully convolutional neural...

This project consists in the implementation of a system that retrieves the five most similar audio files from an audio database when an audio file is presented as the input. I concentrated on indoor and outdoor environmental audio files. Audio is a very important kind of media that includes speech, music and various kinds of environmental noise. With the recent public access to different audio ...

We present the results of our ongoing project researching a tighter coupling between computer and performer. The audio-input radio drum is presented, a simplification of the original apparatus that provides superior latency and resolution. Different demodulation schemes for the amplitude modulated input signals are discussed. Techniques to analyze gesture data are outlined, including eestimatio...

This paper discusses evaluation of content extraction from audio sources. The most straightforward approach is to adapt existing methods for written sources to handle audio input. A transcription then becomes the representation of the audio source in written form; it must capture the word stream, but also other information that aids in decoding the overall structure and content of the audio sou...

We describe the sound design and initial user study of an audio game created for gamers with visual impairments. Despite the wild popularity of platform games such as Super Mario [1] and the development of many audio games over the past decade, the platform genre has so far been all but ignored by audio game designers. To fill this gap and to add to the limited entertainment choices visually im...

This paper presents a system for controlling audio mosaicing with a voice signal, which can be interpreted as a further step in voice-driven sound synthesis. Compared to voice-driven instrumental synthesis, it increases the variety in the synthesized timbre. Also, it provides a more direct interface for audio mosaicing applications, where the performer voice controls rhythmic, tonal and timbre ...

When video is shot in noisy environment, the voice of a speaker seen in the video can be enhanced using the visible mouth movements, reducing background noise. While most existing methods use audio-only inputs, improved performance is obtained with our visual speech enhancement, based on an audio-visual neural network. We add to the training data videos with synthetic background noise taken fro...