Asia-Pacific Signal and Information Processing Association (APSIPA) - Music emotion recognition using deep Gaussian process

2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

Buy Now

Regular:

Music is a powerful force that evokes human emotions. Several investigations of music emotion recognition (MER) have been conducted in recent years. This paper proposes a system for detecting emotion in music that is based on a deep Gaussian process (GP). The system consists of two parts-feature extraction and classification. In the feature extraction part, five types of features that are associated with emotions are selected for representing the music signal; these are rhythm, dynamics, timbre, pitch and tonality. A music clip is decomposed into frames and these features are extracted from each frame. Next, statistical values, such as mean and standard deviation, of frame-based features are calculated to generate a 38-dimensional feature vector. In the classification part, a deep GP is utilized for emotion recognition. We treat classification problem from the perspective of regression. Finally, 9 classes of emotion are categorized by 9 one-versus-all classifiers. The experimental results demonstrate that the proposed system performs well in emotion recognition.

View Less

Related Documents

ASTM D4000-01 - Standard Classification System for Specifying Plastic Materials

December 10, 2001 - ASTM International

1.1 This standard provides a classification system for tabulating the properties of unfilled, filled, and reinforced plastic materials suitable for processing into parts.

Note 1-The classification system may serve many of the needs of industries using plastic materials. The standard ...

ASTM D4066-00 - Standard Classification System for Nylon Injection and Extrusion Materials (PA)

August 10, 2001 - ASTM International

1.1 This classification system covers nylon materials suitable for injection molding and extrusion. Some of these compositions are also suitable for compression molding and application from solution.

1.2 The properties included in this classification system are those required to identify th...

ASTM F2325-03 - Standard Classification for Multi-Layer Steel (MLS) and Other Metal Layer Gaskets for Transportation Applications

October 1, 2003 - ASTM International

1.1 This classification covers a means for specifying Multi-Layer Steel (MLS) and other Metal Layer Gaskets for Transportation Applications by application and construction. These structures are composed of one or more steel or metal layers of material, which may have coatings or embossments. Comm...

ASTM C673-97(2003) - Standard Classification of Fireclay and High-Alumina Plastic Refractories and Ramming Mixes

April 10, 2003 - ASTM International

1.1 This classification covers fireclay and high-alumina plastic refractories and ramming mixes that can be pounded or rammed into place to form a monolithic structure. The terms "plastic" and" ramming mix" are generally intended to describe the workability of the material. In this regard, plasti...

ASTM D5740-03 - Standard Guide for Writing Material Standards in the Classification D4000 Format

July 10, 2003 - ASTM International

1.1 This classification system covers____ materials suitable for________________ . The inclusion or exclusion of recycled plastics in this classification system must be addressed here.

1.2 The properties included in this standard are those required to identify the compositions covered. Ther...

Related Products

Searching for related products...

Related Suppliers

Searching for related suppliers...

Author(s):	Sih-Huei Chen ; Yuan-Shan Lee ; Wen-Chi Hsieh ; Jia-Ching Wang
Publisher:	Asia-Pacific Signal and Information Processing Association (APSIPA)
Publication Date:	1 December 2015
Conference Location:	Hong Kong, China
Conference Date:	16 December 2015
Page(s):	495 - 498
ISBN (Electronic):	978-9-8814-7680-7
DOI:	10.1109/APSIPA.2015.7415321