← Search

Hosang Sung

8 accepted papers

2025

Single-Channel Distance-Based Source Separation for Mobile GPU in Outdoor and Indoor Environments

ICASSP 2025accepted

This study emphasizes the significance of exploring distance-based source separation (DSS) in outdoor environments. Unlike existing studies that primarily focus on indoor settings, the proposed model is designed to capture the unique characteristics of outdoor audio sources. It incorporates advanced…

Cited by 0SourceScholar
2024

FINALLY: fast and universal speech enhancement with studio-like quality

NeurIPS 2024poster

In this paper, we address the challenge of speech enhancement in real-world recordings, which often contain various forms of distortion, such as background noise, reverberation, and microphone artifacts. We revisit the use of Generative Adversarial Networks (GANs) for speech enhancement and theoreti…

2023

Randmasking Augment: A Simple and Randomized Data Augmentation For Acoustic Scene Classification

ICASSP 2023accepted

In this work, we describe RandMasking Augment as an effective data augmentation method for acoustic scene classification research. We concentrate on both time and frequency domains masking augmentation introduced in SpecAugment, and apply various transformations that can maintain time and frequency…

Cited by 0SourceScholar
2015

Flexible spectrum coding in the 3GPP EVS codec

ICASSP 2015accepted

This paper proposes a flexible encoding technique based on multi-stage multiple scale lattice vector quantization and block-constrained trellis coded vector quantization. It is used for the spectrum encoding, more precisely encoding of the LSF parameters, and incorporated in the recently standardize…

Cited by 0SourceScholar
2015

Low bit rate high-quality MDCT audio coding of the 3GPP EVS standard

ICASSP 2015accepted

This paper presents a low bit-rate MDCT coder, which is adopted as a part of the recently standardized codec for Enhanced Voice Services. To maximize codec performance for NB to SWB input signals for low bit-rates (7.2 to 16.4 kbps), new adaptive bit-allocation and spectrum quantization schemes, whi…

Cited by 0SourceScholar
2015

Overview of the EVS codec architecture

ICASSP 2015accepted

The recently standardized 3GPP codec for Enhanced Voice Services (EVS) offers new features and improvements for low-delay real-time communication systems. Based on a novel, switched low-delay speech/audio codec, the EVS codec contains various tools for better compression efficiency and higher qualit…

Cited by 169SourceScholar
2015

Packet-loss concealment technology advances in EVS

ICASSP 2015accepted

EVS, the newly standardized 3GPP Codec for Enhanced Voice Services (EVS) was developed for mobile services such as VoLTE, where error resilience is highly essential. The presented paper outlines all aspects of the advances brought during the EVS development on packet loss concealment, by presenting…

Cited by 25SourceScholar
2015

Session negotiation and media adaptation of EVS in Voice over LTE

ICASSP 2015accepted

EVS is expected to fill the large gap between the quality and capacity currently available and those expected for 4G, and beyond, mobile communications systems. The large bit-rate and bandwidth ranges, and the complex structures of the new codec make it challenging to deploy and operate. In this pap…

Cited by 0SourceScholar