@inproceedings{fei-etal-2024-empathyear,
title = "{E}mpathy{E}ar: An Open-source Avatar Multimodal Empathetic Chatbot",
author = "Fei, Hao and
Zhang, Han and
Wang, Bin and
Liao, Lizi and
Liu, Qian and
Cambria, Erik",
editor = "Cao, Yixin and
Feng, Yang and
Xiong, Deyi",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-demos.7",
doi = "10.18653/v1/2024.acl-demos.7",
pages = "61--71",
abstract = "This paper introduces EmpathyEar, a pioneering open-source, avatar-based multimodal empathetic chatbot, to fill the gap in traditional text-only empathetic response generation (ERG) systems. Leveraging the advancements of a large language model, combined with multimodal encoders and generators, EmpathyEar supports user inputs in any combination of text, sound, and vision, and produces multimodal empathetic responses, offering users, not just textual responses but also digital avatars with talking faces and synchronized speeches. A series of emotion-aware instruction-tuning is performed for comprehensive emotional understanding and generation capabilities. In this way, EmpathyEar provides users with responses that achieve a deeper emotional resonance, closely emulating human-like empathy. The system paves the way for the next emotional intelligence, for which we open-source the code for public access.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fei-etal-2024-empathyear">
<titleInfo>
<title>EmpathyEar: An Open-source Avatar Multimodal Empathetic Chatbot</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Fei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lizi</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qian</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Cambria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yixin</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deyi</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces EmpathyEar, a pioneering open-source, avatar-based multimodal empathetic chatbot, to fill the gap in traditional text-only empathetic response generation (ERG) systems. Leveraging the advancements of a large language model, combined with multimodal encoders and generators, EmpathyEar supports user inputs in any combination of text, sound, and vision, and produces multimodal empathetic responses, offering users, not just textual responses but also digital avatars with talking faces and synchronized speeches. A series of emotion-aware instruction-tuning is performed for comprehensive emotional understanding and generation capabilities. In this way, EmpathyEar provides users with responses that achieve a deeper emotional resonance, closely emulating human-like empathy. The system paves the way for the next emotional intelligence, for which we open-source the code for public access.</abstract>
<identifier type="citekey">fei-etal-2024-empathyear</identifier>
<identifier type="doi">10.18653/v1/2024.acl-demos.7</identifier>
<location>
<url>https://aclanthology.org/2024.acl-demos.7</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>61</start>
<end>71</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EmpathyEar: An Open-source Avatar Multimodal Empathetic Chatbot
%A Fei, Hao
%A Zhang, Han
%A Wang, Bin
%A Liao, Lizi
%A Liu, Qian
%A Cambria, Erik
%Y Cao, Yixin
%Y Feng, Yang
%Y Xiong, Deyi
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F fei-etal-2024-empathyear
%X This paper introduces EmpathyEar, a pioneering open-source, avatar-based multimodal empathetic chatbot, to fill the gap in traditional text-only empathetic response generation (ERG) systems. Leveraging the advancements of a large language model, combined with multimodal encoders and generators, EmpathyEar supports user inputs in any combination of text, sound, and vision, and produces multimodal empathetic responses, offering users, not just textual responses but also digital avatars with talking faces and synchronized speeches. A series of emotion-aware instruction-tuning is performed for comprehensive emotional understanding and generation capabilities. In this way, EmpathyEar provides users with responses that achieve a deeper emotional resonance, closely emulating human-like empathy. The system paves the way for the next emotional intelligence, for which we open-source the code for public access.
%R 10.18653/v1/2024.acl-demos.7
%U https://aclanthology.org/2024.acl-demos.7
%U https://doi.org/10.18653/v1/2024.acl-demos.7
%P 61-71
Markdown (Informal)
[EmpathyEar: An Open-source Avatar Multimodal Empathetic Chatbot](https://aclanthology.org/2024.acl-demos.7) (Fei et al., ACL 2024)
ACL
- Hao Fei, Han Zhang, Bin Wang, Lizi Liao, Qian Liu, and Erik Cambria. 2024. EmpathyEar: An Open-source Avatar Multimodal Empathetic Chatbot. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 61–71, Bangkok, Thailand. Association for Computational Linguistics.