Saturday, October 1, 1:30 pm — 3:00 pm (Rm 403B)
EB4-1 SAE Parametric Equalizer Training: Development of a Technical Ear Training Program Using Max—Mark Bassett, SAE Institute Byron Bay - Byron Bay, NSW, Australia; University of Sydney - Sydney, NSW, Australia; William L. Martens, University of Sydney - Sydney, NSW, Australia
Spectral-based technical ear training (TET) programs generally require the user to identity, by means of matching or absolute identification, one or more parameters of an equalizer applied to a stimulus signal. Numerous TET programs have been developed to date, targeted at either consumers, employees (for in-house training), or students (delivered within educational institutions). Corey’s 2010 suite of programs featured the first commercially available TET programs developed using Max software, deployed as stand-alone applications on CD-ROM. This paper details the development of a new TET program developed in Max, successfully deployed in the Apple App Store. “SAE Parametric Equalizer Training” is a TET application designed to teach students to identify the center frequency of a parametric equalizer applied to any imported audio files.
Engineering Brief 298 (Download now)
EB4-2 Implementation and Demonstration of Applause and Hand-Clapping Feedback System for Live Viewing—Kazuhiko Kawahara, Kyushu University - Fukuoka, Japan; Akiho Fujimori, Kyushu University - Fukuoka-ken, Japan; Yutaka Kamamoto, NTT Communication Science Laboratories - Kanagawa, Japan; Akira Omoto, Kyushu University - Fukuoka, Japan; Onfuture Ltd. - Tokyo, Japan; Takehiro Moriya, NTT Communication Science Labs - Atsugi-shi, Kanagawa-ken, Japan
Recent progress of network capacity enables real-time distribution of high-quality content of multimedia contents. This paper reports on our attempt to transmit the applause and hand-clapping in music concerts. We built a system that has an efficient implementation scheme for low-delay coding of applause and hand-clapping sounds. The system relayed applause and hand-clapping by viewers back to the performance site to provide these sounds in a synthesized and simulated manner. With this system, we conducted an experimental concert using a network distributed site. We observed some interactions between the performers and the receiver site audience. Responses to our questionnaire distributed to the audience and performers also confirmed that applause and hand-clapping feedback were effective for improving the sense of unity established in live viewings.
Engineering Brief 299 (Download now)
EB4-3 Preliminary Experimental Study on Deep Neural Network-Based Dereverberation—Ji Hyun Park, Gwangju Institute of Science and Technology (GIST) - Gwangju, Korea; Kwang Myung Jeon, Gwangju Institute of Science and Technology (GIST) - Gwangju, Korea; Chanjun Chun, Gwangju Institute of Science and Technology (GIST) - Gwangju, Korea; Ji Sang Yoo, Kwangwoon University - Seoul, Korea; Hong Kook Kim, Gwangju Institute of Science and Tech (GIST) - Gwangju, Korea
This paper deals with the issues associated with the dereverberation of speech or audio signals using deep neural networks (DNNs). They include feature extraction for DNNs from both clean and reverberant signals and DNN construction for generating dereverberant signals. To evaluate the performance of the proposed dereverberation method, artificially processed reverberant speech signals are obtained and a feed-forward DNN is constructed. It is shown that log spectral distortion (LSD) after applying DNN-based dereverberation is reduced by around 1.9 dB, compared with that of reverberant speech signals.
Engineering Brief 300 (Download now)
EB4-4 JSAP: A Plugin Standard for the Web Audio API with Intelligent Functionality—Nicholas Jillings, Birmingham City University - Birmingham, UK; Yonghao Wang, Birmingham City University - Birmingham, UK; Joshua D. Reiss, Queen Mary University of London - London, UK; Ryan Stables, Birmingham City University - Birmingham, UK
In digital audio, software plugins are commonly used to implement audio effects and synthesizers, and integrate them with existing software packages. While these plugins have a number of clearly defined formats, a common standard has not been developed for the web, utilizing the Web Audio API. In this paper we present a standard framework that defines the plugin structure and host integration of a plugin. The project facilitates a novel method of cross-adaptive processing where features are transmitted between plugin instances instead of audio routing, saving on multiple calculations of features. The format also enables communication and processing of semantic data with a host server for the collection and utilization of the data to facilitate intelligent music production decisions.
Engineering Brief 301 (Download now)