@inproceedings{chu-etal-2022-self,
title = "Self-supervised Cross-modal Pretraining for Speech Emotion Recognition and Sentiment Analysis",
author = "Chu, Iek-Heng and
Chen, Ziyi and
Yu, Xinlu and
Han, Mei and
Xiao, Jing and
Chang, Peng",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.375",
doi = "10.18653/v1/2022.findings-emnlp.375",
pages = "5105--5114",
abstract = "Multimodal speech emotion recognition (SER) and sentiment analysis (SA) are important techniques for human-computer interaction. Most existing multimodal approaches utilize either shallow cross-modal fusion of pretrained features, or deep cross-modal fusion with raw features. Recently, attempts have been made to fuse pretrained feature representations in a deep fusion manner during fine-tuning stage. However those approaches have not led to improved results, partially due to their relatively simple fusion mechanisms and lack of proper cross-modal pretraining. In this work, leveraging single-modal pretrained models (RoBERTa and HuBERT), we propose a novel deeply-fused audio-text bi-modal transformer with carefully designed cross-modal fusion mechanism and a stage-wise cross-modal pretraining scheme to fully facilitate the cross-modal learning. Our experiment results show that the proposed method achieves state-of-the-art results on the public IEMOCAP emotion and CMU-MOSEI sentiment datasets, exceeding the previous benchmarks by a large margin.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chu-etal-2022-self">
<titleInfo>
<title>Self-supervised Cross-modal Pretraining for Speech Emotion Recognition and Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iek-Heng</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziyi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinlu</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimodal speech emotion recognition (SER) and sentiment analysis (SA) are important techniques for human-computer interaction. Most existing multimodal approaches utilize either shallow cross-modal fusion of pretrained features, or deep cross-modal fusion with raw features. Recently, attempts have been made to fuse pretrained feature representations in a deep fusion manner during fine-tuning stage. However those approaches have not led to improved results, partially due to their relatively simple fusion mechanisms and lack of proper cross-modal pretraining. In this work, leveraging single-modal pretrained models (RoBERTa and HuBERT), we propose a novel deeply-fused audio-text bi-modal transformer with carefully designed cross-modal fusion mechanism and a stage-wise cross-modal pretraining scheme to fully facilitate the cross-modal learning. Our experiment results show that the proposed method achieves state-of-the-art results on the public IEMOCAP emotion and CMU-MOSEI sentiment datasets, exceeding the previous benchmarks by a large margin.</abstract>
<identifier type="citekey">chu-etal-2022-self</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.375</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.375</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>5105</start>
<end>5114</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Self-supervised Cross-modal Pretraining for Speech Emotion Recognition and Sentiment Analysis
%A Chu, Iek-Heng
%A Chen, Ziyi
%A Yu, Xinlu
%A Han, Mei
%A Xiao, Jing
%A Chang, Peng
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F chu-etal-2022-self
%X Multimodal speech emotion recognition (SER) and sentiment analysis (SA) are important techniques for human-computer interaction. Most existing multimodal approaches utilize either shallow cross-modal fusion of pretrained features, or deep cross-modal fusion with raw features. Recently, attempts have been made to fuse pretrained feature representations in a deep fusion manner during fine-tuning stage. However those approaches have not led to improved results, partially due to their relatively simple fusion mechanisms and lack of proper cross-modal pretraining. In this work, leveraging single-modal pretrained models (RoBERTa and HuBERT), we propose a novel deeply-fused audio-text bi-modal transformer with carefully designed cross-modal fusion mechanism and a stage-wise cross-modal pretraining scheme to fully facilitate the cross-modal learning. Our experiment results show that the proposed method achieves state-of-the-art results on the public IEMOCAP emotion and CMU-MOSEI sentiment datasets, exceeding the previous benchmarks by a large margin.
%R 10.18653/v1/2022.findings-emnlp.375
%U https://aclanthology.org/2022.findings-emnlp.375
%U https://doi.org/10.18653/v1/2022.findings-emnlp.375
%P 5105-5114
Markdown (Informal)
[Self-supervised Cross-modal Pretraining for Speech Emotion Recognition and Sentiment Analysis](https://aclanthology.org/2022.findings-emnlp.375) (Chu et al., Findings 2022)
ACL