44 citations · 185 across the 14 of their papers we have counts for
14 papers
FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised Learning
Yeonghyeon Lee, Kangwook Jang, Jahyun Goo +2
Large-scale speech self-supervised learning (SSL) has emerged to the main field of speech processing, however, the problem of computational cost arising from its vast size makes a…
Learning to Maximize Speech Quality Directly Using MOS Prediction for Neural Text-to-Speech
Yeunju Choi, Youngmoon Jung, Youngjoo Suh +1
Although recent neural text-to-speech (TTS) systems have achieved high-quality speech synthesis, there are cases where a TTS system generates low-quality speech, mainly caused by l…
A Unified Deep Learning Framework for Short-Duration Speaker Verification in Adverse Environments
Youngmoon Jung, Yeunju Choi, Hyungjun Lim +1
Speaker verification (SV) has recently attracted considerable research interest due to the growing popularity of virtual assistants. At the same time, there is an increasing requir…
Deep MOS Predictor for Synthetic Speech Using Cluster-Based Modeling
Yeunju Choi, Youngmoon Jung, Hoirin Kim
While deep learning has made impressive progress in speech synthesis and voice conversion, the assessment of the synthesized speech is still carried out by human participants. Seve…
Dynamic Noise Embedding: Noise Aware Training and Adaptation for Speech Enhancement
Joohyung Lee, Youngmoon Jung, Myunghun Jung +1
Estimating noise information exactly is crucial for noise aware training in speech applications including speech enhancement (SE) which is our focus in this paper. To estimate nois…
Neural MOS Prediction for Synthesized Speech Using Multi-Task Learning With Spoofing Detection and Spoofing Type Classification
Yeunju Choi, Youngmoon Jung, Hoirin Kim
Several studies have proposed deep-learning-based models to predict the mean opinion score (MOS) of synthesized speech, showing the possibility of replacing human raters. However,…
Multi-Task Network for Noise-Robust Keyword Spotting and Speaker Verification using CTC-based Soft VAD and Global Query Attention
Myunghun Jung, Youngmoon Jung, Jahyun Goo +1
Keyword spotting (KWS) and speaker verification (SV) have been studied independently although it is known that acoustic and speaker domains are complementary. In this paper, we pro…
Improving Multi-Scale Aggregation Using Feature Pyramid Module for Robust Speaker Verification of Variable-Duration Utterances
Youngmoon Jung, Seong Min Kye, Yeunju Choi +2
Currently, the most widely used approach for speaker verification is the deep speaker embedding learning. In this approach, we obtain a speaker embedding vector by pooling single-s…
Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs
Seong Min Kye, Youngmoon Jung, Hae Beom Lee +2
In practical settings, a speaker recognition system needs to identify a speaker given a short utterance, while the enrollment utterance may be relatively long. However, existing sp…
Dual Attention in Time and Frequency Domain for Voice Activity Detection
Joohyung Lee, Youngmoon Jung, Hoirin Kim
Voice activity detection (VAD) is a challenging task in low signal-to-noise ratio (SNR) environment, especially in non-stationary noise. To deal with this issue, we propose a novel…
Additional Shared Decoder on Siamese Multi-view Encoders for Learning Acoustic Word Embeddings
Myunghun Jung, Hyungjun Lim, Jahyun Goo +2
Acoustic word embeddings --- fixed-dimensional vector representations of arbitrary-length words --- have attracted increasing interest in query-by-example spoken term detection. Re…
Self-Adaptive Soft Voice Activity Detection using Deep Neural Networks for Robust Speaker Verification
Youngmoon Jung, Yeunju Choi, Hoirin Kim
Voice activity detection (VAD), which classifies frames as speech or non-speech, is an important module in many speech applications including speaker verification. In this paper, w…
Spatial Pyramid Encoding with Convex Length Normalization for Text-Independent Speaker Verification
Youngmoon Jung, Younggwan Kim, Hyungjun Lim +2
In this paper, we propose a new pooling method called spatial pyramid encoding (SPE) to generate speaker embeddings for text-independent speaker verification. We first partition th…
Learning acoustic word embeddings with phonetically associated triplet network
Hyungjun Lim, Younggwan Kim, Youngmoon Jung +2
Previous researches on acoustic word embeddings used in query-by-example spoken term detection have shown remarkable performance improvements when using a triplet network. However,…