Conference proceeding
Dual Stage Learning Based Dynamic Time-Frequency Mask Generation For Audio Event Classification
INTERSPEECH 2020, v 2020-, pp 836-840
01 Jan 2020
Abstract
Audio based event recognition becomes quite challenging in real world noisy environments. To alleviate the noise issue, time-frequency mask based feature enhancement methods have been proposed. While these methods with fixed filter settings have been shown to be effective in familiar noise backgrounds, they become brittle when exposed to unexpected noise. To address the unknown noise problem, we develop an approach based on dynamic filter generation learning. In particular, we propose a dual stage dynamic filter generator networks that can be trained to generate a time-frequency mask specifically created for each input audio. Two alternative approaches of training the mask generator network are developed for feature enhancements in high noise environments. Our proposed method shows improved performance and robustness in both clean and unseen noise environments.
Metrics
Details
- Title
- Dual Stage Learning Based Dynamic Time-Frequency Mask Generation For Audio Event Classification
- Creators
- Donghyeon Kim - University of SeoulJaihyun Park - University of SeoulDavid K. Han - DEVCOM Army Research LaboratoryHanseok Ko - University of SeoulInt Speech Commun Assoc
- Publication Details
- INTERSPEECH 2020, v 2020-, pp 836-840
- Series
- Interspeech
- Publisher
- Isca-Int Speech Communication Assoc
- Number of pages
- 5
- Grant note
- US Army Research Laboratory; United States Department of Defense; US Army Research Laboratory (ARL) 2017000210001 / Korea Environmental Industry & Technology Institute (KEITI) through the Public Technology Program - Korean Ministry of Environment (MOE)
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Web of Science ID
- WOS:000833594100173
- Scopus ID
- 2-s2.0-85098177852
- Other Identifier
- 991021930829704721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- International collaboration
- Web of Science research areas
- Audiology & Speech-language Pathology
- Computer Science, Artificial Intelligence
- Computer Science, Software Engineering