44 citations · 63 across the 10 of their papers we have counts for
10 papers
MATE: Matryoshka Audio-Text Embeddings for Open-Vocabulary Keyword Spotting
Youngmoon Jung, Myunghun Jung, Joon-Young Yang +3
Open-vocabulary keyword spotting (KWS) with text-based enrollment has emerged as a flexible alternative to fixed-phrase triggers. Prior utterance-level matching methods, from an em…
Adversarial Deep Metric Learning for Cross-Modal Audio-Text Alignment in Open-Vocabulary Keyword Spotting
Youngmoon Jung, Yong-Hyeok Lee, Myunghun Jung +3
For text enrollment-based open-vocabulary keyword spotting (KWS), acoustic and text embeddings are typically compared at either the phoneme or utterance level. To facilitate this,…
Text-Aware Adapter for Few-Shot Keyword Spotting
Youngmoon Jung, Jinyoung Lee, Seungjin Lee +3
Recent advances in flexible keyword spotting (KWS) with text enrollment allow users to personalize keywords without uttering them during enrollment. However, there is still room fo…
AdaMS: Deep Metric Learning with Adaptive Margin and Adaptive Scale for Acoustic Word Discrimination
Myunghun Jung, Hoirin Kim
Many recent loss functions in deep metric learning are expressed with logarithmic and exponential forms, and they involve margin and scale as essential hyper-parameters. Since each…
Asymmetric Proxy Loss for Multi-View Acoustic Word Embeddings
Myunghun Jung, Hoirin Kim
Acoustic word embeddings (AWEs) are discriminative representations of speech segments, and learned embedding space reflects the phonetic similarity between words. With multi-view l…
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…
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…
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…
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,…