@inproceedings{huang-etal-2021-rcrnn,
title = "{RCRNN}-based Sound Event Detection System with Specific Speech Resolution",
author = "Huang, Sung-Jen and
Wang, Yih-Wen and
Chen, Chia-Ping and
Lu, Chung-Li and
Chan, Bo-Cheng",
editor = "Lee, Lung-Hao and
Chang, Chia-Hui and
Chen, Kuan-Yu",
booktitle = "Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)",
month = oct,
year = "2021",
address = "Taoyuan, Taiwan",
publisher = "The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)",
url = "https://aclanthology.org/2021.rocling-1.16",
pages = "118--123",
abstract = "Sound event detection (SED) system outputs sound events and their time boundaries in audio signals. We proposed an RCRNN-based SED system with residual connection and convolution block attention mechanism based on the mean-teacher framework of semi-supervised learning. The neural network can be trained with an amount of weakly labeled data and unlabeled data. In addition, we consider that the speech event has more information than other sound events. Thus, we use the specific time-frequency resolution to extract the acoustic feature of the speech event. Furthermore, we apply data augmentation and post-processing to improve the performance. On the DCASE 2021 Task 4 validation set, the proposed system achieves the PSDS (Poly-phonic Sound Event Detection Score)-scenario 2 of 57.6{\%} and event-based F1-score of 41.6{\%}, outperforming the baseline score of 52.7{\%} and 40.7{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2021-rcrnn">
<titleInfo>
<title>RCRNN-based Sound Event Detection System with Specific Speech Resolution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sung-Jen</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yih-Wen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chia-Ping</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chung-Li</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo-Cheng</namePart>
<namePart type="family">Chan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lung-Hao</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chia-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kuan-Yu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)</publisher>
<place>
<placeTerm type="text">Taoyuan, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sound event detection (SED) system outputs sound events and their time boundaries in audio signals. We proposed an RCRNN-based SED system with residual connection and convolution block attention mechanism based on the mean-teacher framework of semi-supervised learning. The neural network can be trained with an amount of weakly labeled data and unlabeled data. In addition, we consider that the speech event has more information than other sound events. Thus, we use the specific time-frequency resolution to extract the acoustic feature of the speech event. Furthermore, we apply data augmentation and post-processing to improve the performance. On the DCASE 2021 Task 4 validation set, the proposed system achieves the PSDS (Poly-phonic Sound Event Detection Score)-scenario 2 of 57.6% and event-based F1-score of 41.6%, outperforming the baseline score of 52.7% and 40.7%.</abstract>
<identifier type="citekey">huang-etal-2021-rcrnn</identifier>
<location>
<url>https://aclanthology.org/2021.rocling-1.16</url>
</location>
<part>
<date>2021-10</date>
<extent unit="page">
<start>118</start>
<end>123</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RCRNN-based Sound Event Detection System with Specific Speech Resolution
%A Huang, Sung-Jen
%A Wang, Yih-Wen
%A Chen, Chia-Ping
%A Lu, Chung-Li
%A Chan, Bo-Cheng
%Y Lee, Lung-Hao
%Y Chang, Chia-Hui
%Y Chen, Kuan-Yu
%S Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)
%D 2021
%8 October
%I The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)
%C Taoyuan, Taiwan
%F huang-etal-2021-rcrnn
%X Sound event detection (SED) system outputs sound events and their time boundaries in audio signals. We proposed an RCRNN-based SED system with residual connection and convolution block attention mechanism based on the mean-teacher framework of semi-supervised learning. The neural network can be trained with an amount of weakly labeled data and unlabeled data. In addition, we consider that the speech event has more information than other sound events. Thus, we use the specific time-frequency resolution to extract the acoustic feature of the speech event. Furthermore, we apply data augmentation and post-processing to improve the performance. On the DCASE 2021 Task 4 validation set, the proposed system achieves the PSDS (Poly-phonic Sound Event Detection Score)-scenario 2 of 57.6% and event-based F1-score of 41.6%, outperforming the baseline score of 52.7% and 40.7%.
%U https://aclanthology.org/2021.rocling-1.16
%P 118-123
Markdown (Informal)
[RCRNN-based Sound Event Detection System with Specific Speech Resolution](https://aclanthology.org/2021.rocling-1.16) (Huang et al., ROCLING 2021)
ACL
- Sung-Jen Huang, Yih-Wen Wang, Chia-Ping Chen, Chung-Li Lu, and Bo-Cheng Chan. 2021. RCRNN-based Sound Event Detection System with Specific Speech Resolution. In Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021), pages 118–123, Taoyuan, Taiwan. The Association for Computational Linguistics and Chinese Language Processing (ACLCLP).