3 citations · 7 across the 8 of their papers we have counts for
8 papers
MoNe: Modular Neural Memory for Efficient Long Context Inference
Wonguk Cho, Kyubyung Chae, Tribhuvanesh Orekondy +6
We present MoNe, a lightweight modular neural memory that attaches to any frozen pretrained Transformer to enable long-context inference without retraining. MoNe reads context in f…
Knowledge Distillation from Non-streaming to Streaming ASR Encoder using Auxiliary Non-streaming Layer
Kyuhong Shim, Jinkyu Lee, Simyung Chang +1
Streaming automatic speech recognition (ASR) models are restricted from accessing future context, which results in worse performance compared to the non-streaming models. To improv…
SubSpectral Normalization for Neural Audio Data Processing
Simyung Chang, Hyoungwoo Park, Janghoon Cho +3
Convolutional Neural Networks are widely used in various machine learning domains. In image processing, the features can be obtained by applying 2D convolution to all spatial dimen…
Weakly Labeled Sound Event Detection Using Tri-training and Adversarial Learning
Hyoungwoo Park, Sungrack Yun, Jungyun Eum +2
This paper considers a semi-supervised learning framework for weakly labeled polyphonic sound event detection problems for the DCASE 2019 challenge's task4 by combining both the tr…
Acoustic Scene Classification Based on a Large-margin Factorized CNN
Janghoon Cho, Sungrack Yun, Hyoungwoo Park +2
In this paper, we present an acoustic scene classification framework based on a large-margin factorized convolutional neural network (CNN). We adopt the factorized CNN to learn the…
Orthogonality Constrained Multi-Head Attention For Keyword Spotting
Mingu Lee, Jinkyu Lee, Hye Jin Jang +3
Multi-head attention mechanism is capable of learning various representations from sequential data while paying attention to different subsequences, e.g., word-pieces or syllables…
Query-by-example on-device keyword spotting
Byeonggeun Kim, Mingu Lee, Jinkyu Lee +2
A keyword spotting (KWS) system determines the existence of, usually predefined, keyword in a continuous speech stream. This paper presents a query-by-example on-device KWS system…
An End-to-End Text-independent Speaker Verification Framework with a Keyword Adversarial Network
Sungrack Yun, Janghoon Cho, Jungyun Eum +2
This paper presents an end-to-end text-independent speaker verification framework by jointly considering the speaker embedding (SE) network and automatic speech recognition (ASR) n…