Automatic Intelligibility Assessment of Dysarthric Speech Using Phonologically-Structured Sparse Linear Model von Kim, Myung Jong, Kim, Younggwan, Kim, Hoirin

Volltext

A Unified Deep Learning Framework for Short-Duration Speaker Verification in Adverse Environments von Jung, Youngmoon, Choi, Yeunju, Lim, Hyungjun, Kim, Hoirin

Volltext

Multiple Acoustic Model-Based Discriminative Likelihood Ratio Weighting for Voice Activity Detection von Suh, Youngjoo, Kim, Hoirin

Volltext

Learning to Maximize Speech Quality Directly Using MOS Prediction for Neural Text-to-Speech von Choi, Yeunju, Jung, Youngmoon, Suh, Youngjoo, Kim, Hoirin

Volltext

Probabilistic Class Histogram Equalization Based on Posterior Mean Estimation for Robust Speech Recognition von Suh, Youngjoo, Kim, Hoirin

Volltext

Audio-Based Objectionable Content Detection Using Discriminative Transforms of Time-Frequency Dynamics von Myung Jong Kim, Hoirin Kim

Volltext

Learning Self-Informed Feature Contribution for Deep Learning-Based Acoustic Modeling von Kim, Younggwan, Kim, Myungjong, Goo, Jahyun, Kim, Hoirin

Volltext

Environmental Model Adaptation Based on Histogram Equalization von Youngjoo Suh, Youngjoo Suh, Hoirin Kim, Hoirin Kim

Volltext

Probabilistic Class Histogram Equalization for Robust Speech Recognition von Suh, Y, Mikyong Ji, Mikyong Ji, Hoirin Kim, Hoirin Kim

Volltext

Text-Independent Speaker Identification using Soft Channel Selection in Home Robot Environments von Mikyong Ji, Mikyong Ji, Sungtak Kim, Sungtak Kim, Hoirin Kim, Hoirin Kim, Ho-Sub Yoon, Ho-Sub Yoon

Volltext

Histogram equalization with Bayesian estimation for noise robust speech recognition von Suh, Youngjoo, Kim, Hoirin

Volltext

Reliable likelihood ratios for statistical model-based voice activity detector with low false-alarm rate von Kim, Younggwan, Suh, Youngjoo, Kim, Hoirin

Volltext

Cross-Informed Domain Adversarial Training for Noise-Robust Wake-Up Word Detection von Lim, Hyungjun, Kim, Younggwan, Kim, Hoirin

Volltext

Histogram Equalization to Model Adaptation for Robust Speech Recognition von Suh, Youngjoo, Kim, Hoirin

Volltext

Histogram Equalization to Model Adaptation for Robust Speech Recognition von Suh, Youngjoo, Kim, Hoirin

Volltext

Interlayer Selective Attention Network for Robust Personalized Wake-Up Word Detection von Lim, Hyungjun, Kim, Younggwan, Goo, Jahyun, Kim, Hoirin

Volltext

Cepstral Domain Feature Extraction Utilizing Entropic Distance-Based Filterbank von SUH, Youngjoo, KIM, Hoirin

Volltext

Minimum classification error-based weighted support vector machine kernels for speaker verification von Suh, Youngjoo, Kim, Hoirin

Volltext

Acoustic Model Combination Incorporated With Mask-Based Multi-Channel Source Separation for Automatic Speech Recognition von Yoon, Jae Sam, Park, Ji Hun, Kim, Hong Kook, Kim, Hoirin

Volltext

Discriminative likelihood score weighting based on acoustic-phonetic classification for speaker identification von Suh, Youngjoo, Kim, Hoirin

Volltext