Conference proceeding
R-CRNN: Region-based Convolutional Recurrent Neural Network for Audio Event Detection: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES
19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6, pp.1358-1362
Interspeech
01/01/2018
DOI: 10.21437/Interspeech.2018-2323
Abstract
This paper proposes a Region-based Convolutional Recurrent Neural Network (R-CRNN) for audio event detection (AED). The proposed network is inspired by Faster-RCNN [I], a wellknown region-based convolutional network framework for visual object detection. Different from the original Faster-RCNN, a recurrent layer is added on top of the convolutional network to capture the long-term temporal context from the extracted high-level features. While most of the previous works on AED generate predictions at frame level first, and then use post-processing to predict the onset/offset timestamps of events from a probability sequence; the proposed method generates predictions at event level directly and can be trained end-to-end with a multitask loss, which optimizes the classification and localization of audio events simultaneously. The proposed method is tested on DCASE 2017 Challenge dataset [2]. To the best of our knowledge, R-CRNN is the best performing single-model method among all methods without using ensembles both on development and evaluation sets. Compared to the other region-based network for AED (R-FCN [3]) with an event-based error rate (ER) of 0.18 on the development set, our method reduced the ER to half.
Details
- Title: Subtitle
- R-CRNN: Region-based Convolutional Recurrent Neural Network for Audio Event Detection: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES
- Creators
- Chieh-Chi Kao - Amazon Alexa, Cambridge, MA 02142 USAWeiran Wang - Amazon Alexa, Cambridge, MA 02142 USAMing Sun - Amazon Alexa, Cambridge, MA 02142 USAChao Wang - Amazon Alexa, Cambridge, MA 02142 USA
- Resource Type
- Conference proceeding
- Publication Details
- 19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6, pp.1358-1362
- Publisher
- Isca-Int Speech Communication Assoc
- Series
- Interspeech
- DOI
- 10.21437/Interspeech.2018-2323
- ISSN
- 2308-457X
- Number of pages
- 5
- Language
- English
- Date published
- 01/01/2018
- Academic Unit
- Computer Science
- Record Identifier
- 9984696566302771
Metrics
6 Record Views