@inproceedings{figueroa-etal-2024-mhm,
title = "Mhm... Yeah? Okay! Evaluating the Naturalness and Communicative Function of Synthesized Feedback Responses in Spoken Dialogue",
author = "Figueroa, Carol and
de Korte, Marcel and
Ochs, Magalie and
Skantze, Gabriel",
editor = "Kawahara, Tatsuya and
Demberg, Vera and
Ultes, Stefan and
Inoue, Koji and
Mehri, Shikib and
Howcroft, David and
Komatani, Kazunori",
booktitle = "Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = sep,
year = "2024",
address = "Kyoto, Japan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.sigdial-1.46",
doi = "10.18653/v1/2024.sigdial-1.46",
pages = "544--553",
abstract = "To create conversational systems with human-like listener behavior, generating short feedback responses (e.g., {``}mhm{''}, {``}ah{''}, {``}wow{''}) appropriate for their context is crucial. These responses convey their communicative function through their lexical form and their prosodic realization. In this paper, we transplant the prosody of feedback responses from human-human U.S. English telephone conversations to a target speaker using two synthesis techniques (TTS and signal processing). Our evaluation focuses on perceived naturalness, contextual appropriateness and preservation of communicative function. Results indicate TTS-generated feedback were perceived as more natural than signal-processing-based feedback, with no significant difference in appropriateness. However, the TTS did not consistently convey the communicative function of the original feedback.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="figueroa-etal-2024-mhm">
<titleInfo>
<title>Mhm... Yeah? Okay! Evaluating the Naturalness and Communicative Function of Synthesized Feedback Responses in Spoken Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carol</namePart>
<namePart type="family">Figueroa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcel</namePart>
<namePart type="family">de Korte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Magalie</namePart>
<namePart type="family">Ochs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Skantze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tatsuya</namePart>
<namePart type="family">Kawahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Ultes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koji</namePart>
<namePart type="family">Inoue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shikib</namePart>
<namePart type="family">Mehri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Howcroft</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazunori</namePart>
<namePart type="family">Komatani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyoto, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To create conversational systems with human-like listener behavior, generating short feedback responses (e.g., “mhm”, “ah”, “wow”) appropriate for their context is crucial. These responses convey their communicative function through their lexical form and their prosodic realization. In this paper, we transplant the prosody of feedback responses from human-human U.S. English telephone conversations to a target speaker using two synthesis techniques (TTS and signal processing). Our evaluation focuses on perceived naturalness, contextual appropriateness and preservation of communicative function. Results indicate TTS-generated feedback were perceived as more natural than signal-processing-based feedback, with no significant difference in appropriateness. However, the TTS did not consistently convey the communicative function of the original feedback.</abstract>
<identifier type="citekey">figueroa-etal-2024-mhm</identifier>
<identifier type="doi">10.18653/v1/2024.sigdial-1.46</identifier>
<location>
<url>https://aclanthology.org/2024.sigdial-1.46</url>
</location>
<part>
<date>2024-09</date>
<extent unit="page">
<start>544</start>
<end>553</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mhm... Yeah? Okay! Evaluating the Naturalness and Communicative Function of Synthesized Feedback Responses in Spoken Dialogue
%A Figueroa, Carol
%A de Korte, Marcel
%A Ochs, Magalie
%A Skantze, Gabriel
%Y Kawahara, Tatsuya
%Y Demberg, Vera
%Y Ultes, Stefan
%Y Inoue, Koji
%Y Mehri, Shikib
%Y Howcroft, David
%Y Komatani, Kazunori
%S Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2024
%8 September
%I Association for Computational Linguistics
%C Kyoto, Japan
%F figueroa-etal-2024-mhm
%X To create conversational systems with human-like listener behavior, generating short feedback responses (e.g., “mhm”, “ah”, “wow”) appropriate for their context is crucial. These responses convey their communicative function through their lexical form and their prosodic realization. In this paper, we transplant the prosody of feedback responses from human-human U.S. English telephone conversations to a target speaker using two synthesis techniques (TTS and signal processing). Our evaluation focuses on perceived naturalness, contextual appropriateness and preservation of communicative function. Results indicate TTS-generated feedback were perceived as more natural than signal-processing-based feedback, with no significant difference in appropriateness. However, the TTS did not consistently convey the communicative function of the original feedback.
%R 10.18653/v1/2024.sigdial-1.46
%U https://aclanthology.org/2024.sigdial-1.46
%U https://doi.org/10.18653/v1/2024.sigdial-1.46
%P 544-553
Markdown (Informal)
[Mhm... Yeah? Okay! Evaluating the Naturalness and Communicative Function of Synthesized Feedback Responses in Spoken Dialogue](https://aclanthology.org/2024.sigdial-1.46) (Figueroa et al., SIGDIAL 2024)
ACL