Search Results - "Shon, Suwon"

Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification by Sarkar, Achintya Kumar, Zheng-Hua Tan, Hao Tang, Suwon Shon, Glass, James

“…There are a number of studies about extraction of bottleneck (BN) features from deep neural networks (DNNs) trained to discriminate speakers, pass-phrases, and…”
Get full text

Deep Neural Network based learning and transferring mid-level audio features for acoustic scene classification by Seongkyu Mun, Suwon Shon, Wooil Kim, Han, David K., Hanseok Ko

“…Deep Neural Network (DNN) based transfer learning has been shown to be effective in Visual Object Classification (VOC) for complementing the deficit of target…”
Get full text

Robust speaker direction estimation with microphone array using NMF for smart TV interaction by Seongkyu Mun, Suwon Shon, Wooil Kim, Hanseok Ko

“…This paper proposes a robust speaker direction estimation method based on a microphone array for voice based interaction with smart TV. The proposed method…”
Get full text

MIT-QCRI Arabic dialect identification system for the 2017 multi-genre broadcast challenge by Suwon Shon, Ali, Ahmed, Glass, James

“…In order to successfully annotate the Arabic speech content found in open-domain media broadcasts, it is essential to be able to process a diverse set of…”
Get full text

Sudden noise source localization system for intelligent automobile application with acoustic sensors by Suwon Shon, Kim, Eric, Jongsung Yoon, Hanseok Ko

“…This paper suggests an automotive application for finding direction of sudden noise source in driving situation. The system applies sound source localization…”
Get full text

Domain Mismatch Robust Acoustic Scene Classification Using Channel Information Conversion by Mun, Seongkyu, Shon, Suwon

“…In recent acoustic scene classification (ASC) research field, training and test device channel mismatch have become an issue for the real world implementation…”
Get full text

Noise-tolerant Audio-visual Online Person Verification Using an Attention-based Neural Network Fusion by Shon, Suwon, Oh, Tae-Hyun, Glass, James

“…In this paper, we present a multi-modal online person verification system using both speech and visual signals. Inspired by neuroscientific findings on the…”
Get full text

ADI17: A Fine-Grained Arabic Dialect Identification Dataset by Shon, Suwon, Ali, Ahmed, Samih, Younes, Mubarak, Hamdy, Glass, James

“…In this paper, we describe a method to collect dialectal speech from YouTube videos to create a large-scale Dialect Identification (DID) dataset. Using this…”
Get full text

Improving ASR Contextual Biasing with Guided Attention by Tang, Jiyang, Kim, Kwangyoun, Shon, Suwon, Wu, Felix, Sridhar, Prashant

“…In this paper, we propose a Guided Attention (GA) auxiliary training loss, which improves the effectiveness and robustness of automatic speech recognition…”
Get full text

SLUE: New Benchmark Tasks For Spoken Language Understanding Evaluation on Natural Speech by Shon, Suwon, Pasad, Ankita, Wu, Felix, Brusco, Pablo, Artzi, Yoav, Livescu, Karen, Han, Kyu J.

“…Progress in speech processing has been facilitated by shared datasets and benchmarks. Historically these have focused on automatic speech recognition (ASR),…”
Get full text

Domain Attentive Fusion for End-to-end Dialect Identification with Unknown Target Domain by Shon, Suwon, Ali, Ahmed, Glass, James

“…End-to-end deep learning language or dialect identification systems operate on the spectrogram or other acoustic feature and directly generate identification…”
Get full text

Exploiting Convolutional Neural Networks for Phonotactic Based Dialect Identification by Najafian, Maryam, Khurana, Sameer, Shan, Suwon, Ali, Ahmed, Glass, James

“…In this paper, we investigate different approaches for Dialect Identification (DID) in Arabic broadcast speech. Dialects differ in their inventory of…”
Get full text

Generative Context-Aware Fine-Tuning of Self-Supervised Speech Models by Shon, Suwon, Kim, Kwangyoun, Sridhar, Prashant, Hsu, Yi-Te, Watanabe, Shinji, Livescu, Karen

“…When performing tasks like automatic speech recognition or spoken language understanding for a given utterance, access to preceding text or audio provides…”
Get full text

Context-Aware Fine-Tuning of Self-Supervised Speech Models by Shon, Suwon, Wu, Felix, Kim, Kwangyoun, Sridhar, Prashant, Livescu, Karen, Watanabe, Shinji

“…Self-supervised pre-trained transformers have improved the state of the art on a variety of speech tasks. Due to the quadratic time and space complexity of…”
Get full text

Generalized cross-correlation based noise robust abnormal acoustic event localization utilizing non-negative matrix factorization by Sungkyu Moon, Suwon Shon, Wooil Kim, Han, David K.

“…In this paper, robust sound source localization for surveillance system is presented. In particular, we propose an algorithm for abnormal acoustic event…”
Get full text

Maximum likelihood Linear Dimension Reduction of heteroscedastic feature for robust Speaker Recognition by Suwon Shon, Seongkyu Mun, Han, David K., Hanseok Ko

“…This paper analyzes heteroscedasticity in i-vector for robust forensics and surveillance speaker recognition system. Linear Discriminant Analysis (LDA), a…”
Get full text

Abnormal acoustic event localization based on selective frequency bin in high noise environment for audio surveillance by Suwon Shon, Han, David K., Hanseok Ko

“…In this paper, a method for source localization for surveillance system is presented. In particular, we propose an algorithm for abnormal acoustic event…”
Get full text

Motion primitives for designing flexible gesture set in Human-Robot Interface by Suwon Shon, Jounghoon Beh, Cheoljong Yang, Han, D. K., Hanseok Ko

“…This paper proposes motion primitives for designing a gesture set in a gesture recognition system as Human-Robot Interface (HRI). Based on statistical analyses…”
Get full text

The MGB-5 Challenge: Recognition and Dialect Identification of Dialectal Arabic Speech by Ali, Ahmed, Shon, Suwon, Samih, Younes, Mubarak, Hamdy, Abdelali, Ahmed, Glass, James, Renals, Steve, Choukri, Khalid

“…This paper describes the fifth edition of the Multi-Genre Broadcast Challenge (MGB-5), an evaluation focused on Arabic speech recognition and dialect…”
Get full text

Frame-Level Speaker Embeddings for Text-Independent Speaker Recognition and Analysis of End-to-End Model by Shon, Suwon, Tang, Hao, Glass, James

“…In this paper, we propose a Convolutional Neural Network (CNN) based speaker recognition model for extracting robust speaker embeddings. The embedding can be…”
Get full text