Tae-Jin Lee

Speech emotion recognition using convolutional and Recurrent Neural Networks

With rapid developments in the design of deep architecture models and learning algorithms, methods referred to as deep learning have come to be widely used in a variety of research areas such as pattern recognition, classification, and signal processing. Deep learning methods are being applied in various recognition tasks such as image, speech, and music recognition. Convolutional Neural Networks (CNNs) especially show remarkable recognition performance for computer vision tasks. In addition, Recurrent Neural Networks (RNNs) show considerable success in many sequential data processing tasks. In this study, we investigate the result of the Speech Emotion Recognition (SER) algorithm based on CNNs and RNNs trained using an emotional speech database. The main goal of our work is to propose a SER method based on concatenated CNNs and RNNs without using any traditional hand-crafted features. By applying the proposed methods to an emotional speech database, the classification result was verified to have better accuracy than that achieved using conventional classification methods.

Spatial Cue Based Sound Scene Control for MPEG Surround

Spatial audio coding scheme is advanced technology in the sense of saving bitrate without any scarifications of sound quality. In this paper, the method to utilizing the spatial cues is present. This utilization is for supporting a new useful functionality, i.e., flexible sound scene control. The function of sound scene control may result in providing user preferable audio service by interaction and be utilized in upcoming applications such as multi-view video service and virtual reality applications. It will be shown that even with a little addition of computational operations; this useful functionality will be achievable maintaining the corresponding sound quality.

Personalized Audio Broadcasting System through the Terrestrial- DMB System

This paper describes the personalized audio broadcasting services through the terrestrial digital multimedia broadcasting (T-DMB) system. This system consists of preprocessing module, authoring module, T-DMB transmission/reception module and playing terminal. Through this system user can control the 3D audio scene freely or choose the preset 3D audio scene. This system can be applied to DMB, 3DTV and home shopping applications to provide interactivity and realistic feelings.

Harmonic and percussive source separation using a convolutional auto encoder

Real world audio signals are generally a mixture of harmonic and percussive sounds. In this paper, we present a novel method for separating the harmonic and percussive audio signals from an audio mixture. Proposed method involves the use of a convolutional auto-encoder on a magnitude of the spectrogram to separate the harmonic and percussive signals. This network structure enables automatic high-level feature learning and spectral domain audio decomposition. An evaluation was performed using professionally produced music recording. Consequently, we confirm that the proposed method provides superior separation performance compared to conventional methods.

A Study on Realistic Sound Reproduction for UHDTV

&()x17x18*+x14,-.x17x18/01234HDTVx0ex1f5UHDTV x1c6789:; ?@Ax1fx17x1dBx11CDEFG. x1fHI>HDTVHx1c5.1JKx1c>LMBLMx0e N Ox13x14x13x17x18:UHDTV Px1a/:;Q34,Rx10x1c67x0e STU x1cx8aH x1c?UHDTV Hx8bx8cx10x11x12x13x14x13x17x18Hx1ax10Ex8d2x1fQx8ex8fx84Sx1ft.Mx13x14x13x17x18/x90x91x92]*8x1dHx1c/x15x16m Hx1agx1cx17x18SEx93x941x895Ex8dgx95Ex96x10G. AbstractOwing to the latest development of component and media processing technologies, UHDTV as a successor of the HDTV is expected that this will be coming soon realization. Accordingly, an audio technology that provides a 5.1-channel surround sound in home should be contemplating on what services should be provided with the advent of UHDTV era. In fact, however, the market of 5.1-channel audio is struggling, due to the difficulty of installation and maintenance of the multi speakers in a home. Meanwhile, the movie sound market for a long time been used in 5.1 and 7.1-channel sound formats, have changed as Dolby ATMOS, IOSONO, AURO3D etc. are launched one after another with the introduction of hybrid audio technologies that include the ceiling and object-based sounds. This very object-based audio technology is assured to be introduced in the home theater and broadcast audio market, and this change in audio technology is expected to be a breath of pioneering technological advances and market growth from the channel-based audio market that lacks flexibility. In this paper, we will investigate a suitable realistic audio solution for UHDTV, and introduce hybrid audio technologies, which is expected to be an audio technology for UHDTV, and we will describe the hybrid audio content format and reproduction methods in a home and consider the future prospects of realistic audio.Keyword : UHD Audio, Realistic Audio, Object-based Audio, UHDTV, Audio Renderingx97x98(Special Paper) 20 1 , 2015 1(JBE Vol. 20, No. 1, January 2015)http://dx.doi.org/10.5909/JBE.2015.20.1.68ISSN 2287-9137 (Online) ISSN 1226-7953 (Print)

MPEG Audio New Standard: USAC Technology

,J KLM/

Multichannel Audio Reproduction Technology based on 10.2ch for UHDTV

NO> PQR3x16x17Sx19M

Implementation of multi-channel AAC encoder for high quality audio broadcasting

x15TU3 1x0fVWXY, Z[N]Wx1d^I4Z_L2 Q

The high-quality audio broadcasting system using MPEG-2 AAC and streaming technology

x1a`a Wx1dbx13cdex1dSfg,. hijk3lx1a`a Wx1dbx13cdWXY, MPEGWm

Apparatus and method for coding and decoding multi-object audio signal with various channel

2007?10@82n(WmCfPo-pU3USAC ao-pQqf, 2011?7@97n(WmFDISr/stQq,. MPEG-D USAC jZ[x1a`a tAMR-WB+hx1a`a tHE-AAC V2ox16x17 3;u` (v[WXYwx19x1dxx1a`a3AAC, ACELP, TCX y,Jx15z{QRo|}Q~x1a`ao45Qf, fx1dxx1a`a 3