RQNet: Residual quaternion CNN for performance enhancement in low complexity and device robust acoustic scene classification
Acoustic Scene Classification aims to recognize the unique acoustic characteristics of an
environment. Recently, Convolutional Neural Networks (CNNs) have boosted the accuracy …
environment. Recently, Convolutional Neural Networks (CNNs) have boosted the accuracy …
Dummy prototypical networks for few-shot open-set keyword spotting
Keyword spotting is the task of detecting a keyword in streaming audio. Conventional
keyword spotting targets predefined keywords classification, but there is growing attention in …
keyword spotting targets predefined keywords classification, but there is growing attention in …
[PDF][PDF] Multi-Scale Architecture and Device-Aware Data-Random-Drop Based Fine-Tuning Method for Acoustic Scene Classification.
We propose a low-complexity acoustic scene classification (ASC) model structure suitable
for short-segmented audio and fine-tuning methods for generalization to multiple recording …
for short-segmented audio and fine-tuning methods for generalization to multiple recording …
Randmasking augment: A simple and randomized data augmentation for acoustic scene classification
J Han, M Matuszewski, O Sikorski… - ICASSP 2023-2023 …, 2023 - ieeexplore.ieee.org
In this work, we describe RandMasking Augment as an effective data augmentation method
for acoustic scene classification research. We concentrate on both time and frequency …
for acoustic scene classification research. We concentrate on both time and frequency …
Efficient Lightweight Speaker Verification With Broadcasting CNN-Transformer and Knowledge Distillation Training of Self-Attention Maps
Developing a lightweight speaker embedding extractor (SEE) is crucial for the practical
implementation of automatic speaker verification (ASV) systems. To this end, we recently …
implementation of automatic speaker verification (ASV) systems. To this end, we recently …
Domain agnostic few-shot learning for speaker verification
Deep learning models for verification systems often fail to generalize to new users and new
environments, even though they learn highly discriminative features. To address this …
environments, even though they learn highly discriminative features. To address this …
Synthetic data generation techniques for training deep acoustic siren identification networks
Acoustic sensing has been widely exploited for the early detection of harmful situations in
urban environments: in particular, several siren identification algorithms based on deep …
urban environments: in particular, several siren identification algorithms based on deep …
[PDF][PDF] HYU Submission for The Dcase 2022: Fine-tuning method using device-aware data-random-drop for device-imbalanced acoustic scene classification
JH Lee, JH Choi, PM Byun… - Detection Classif. Acoust …, 2022 - dcase.community
This paper address the Hanyang University team submission for the DCASE 2022
Challenge Low-Complexity Acoustic Scene Classification task. The task aims to design a …
Challenge Low-Complexity Acoustic Scene Classification task. The task aims to design a …
Instance-level loss based multiple-instance learning framework for acoustic scene classification
WG Choi, JH Chang, JM Yang, HG Moon - Applied Acoustics, 2024 - Elsevier
An acoustic scene is inferred by detecting properties combining diverse sounds and
acoustic environments. This study is intended to discover these properties effectively using …
acoustic environments. This study is intended to discover these properties effectively using …
Towards domain generalisation in asr with elitist sampling and ensemble knowledge distillation
Knowledge distillation (KD) has widely been used for model compression and domain
adaptation for speech applications. In the presence of multiple teachers, knowledge can …
adaptation for speech applications. In the presence of multiple teachers, knowledge can …