@inproceedings{min-etal-2021-evaluating,
title = "Evaluating Automatic Speech Recognition Quality and Its Impact on Counselor Utterance Coding",
author = "Min, Do June and
P{\'e}rez-Rosas, Ver{\'o}nica and
Mihalcea, Rada",
editor = "Goharian, Nazli and
Resnik, Philip and
Yates, Andrew and
Ireland, Molly and
Niederhoffer, Kate and
Resnik, Rebecca",
booktitle = "Proceedings of the Seventh Workshop on Computational Linguistics and Clinical Psychology: Improving Access",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.clpsych-1.18",
doi = "10.18653/v1/2021.clpsych-1.18",
pages = "159--168",
abstract = "Automatic speech recognition (ASR) is a crucial step in many natural language processing (NLP) applications, as often available data consists mainly of raw speech. Since the result of the ASR step is considered as a meaningful, informative input to later steps in the NLP pipeline, it is important to understand the behavior and failure mode of this step. In this work, we analyze the quality of ASR in the psychotherapy domain, using motivational interviewing conversations between therapists and clients. We conduct domain agnostic and domain-relevant evaluations using standard evaluation metrics and also identify domain-relevant keywords in the ASR output. Moreover, we empirically study the effect of mixing ASR and manual data during the training of a downstream NLP model, and also demonstrate how additional local context can help alleviate the error introduced by noisy ASR transcripts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="min-etal-2021-evaluating">
<titleInfo>
<title>Evaluating Automatic Speech Recognition Quality and Its Impact on Counselor Utterance Coding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Do</namePart>
<namePart type="given">June</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verónica</namePart>
<namePart type="family">Pérez-Rosas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rada</namePart>
<namePart type="family">Mihalcea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Workshop on Computational Linguistics and Clinical Psychology: Improving Access</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nazli</namePart>
<namePart type="family">Goharian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philip</namePart>
<namePart type="family">Resnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Yates</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Molly</namePart>
<namePart type="family">Ireland</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kate</namePart>
<namePart type="family">Niederhoffer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Resnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic speech recognition (ASR) is a crucial step in many natural language processing (NLP) applications, as often available data consists mainly of raw speech. Since the result of the ASR step is considered as a meaningful, informative input to later steps in the NLP pipeline, it is important to understand the behavior and failure mode of this step. In this work, we analyze the quality of ASR in the psychotherapy domain, using motivational interviewing conversations between therapists and clients. We conduct domain agnostic and domain-relevant evaluations using standard evaluation metrics and also identify domain-relevant keywords in the ASR output. Moreover, we empirically study the effect of mixing ASR and manual data during the training of a downstream NLP model, and also demonstrate how additional local context can help alleviate the error introduced by noisy ASR transcripts.</abstract>
<identifier type="citekey">min-etal-2021-evaluating</identifier>
<identifier type="doi">10.18653/v1/2021.clpsych-1.18</identifier>
<location>
<url>https://aclanthology.org/2021.clpsych-1.18</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>159</start>
<end>168</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Automatic Speech Recognition Quality and Its Impact on Counselor Utterance Coding
%A Min, Do June
%A Pérez-Rosas, Verónica
%A Mihalcea, Rada
%Y Goharian, Nazli
%Y Resnik, Philip
%Y Yates, Andrew
%Y Ireland, Molly
%Y Niederhoffer, Kate
%Y Resnik, Rebecca
%S Proceedings of the Seventh Workshop on Computational Linguistics and Clinical Psychology: Improving Access
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F min-etal-2021-evaluating
%X Automatic speech recognition (ASR) is a crucial step in many natural language processing (NLP) applications, as often available data consists mainly of raw speech. Since the result of the ASR step is considered as a meaningful, informative input to later steps in the NLP pipeline, it is important to understand the behavior and failure mode of this step. In this work, we analyze the quality of ASR in the psychotherapy domain, using motivational interviewing conversations between therapists and clients. We conduct domain agnostic and domain-relevant evaluations using standard evaluation metrics and also identify domain-relevant keywords in the ASR output. Moreover, we empirically study the effect of mixing ASR and manual data during the training of a downstream NLP model, and also demonstrate how additional local context can help alleviate the error introduced by noisy ASR transcripts.
%R 10.18653/v1/2021.clpsych-1.18
%U https://aclanthology.org/2021.clpsych-1.18
%U https://doi.org/10.18653/v1/2021.clpsych-1.18
%P 159-168
Markdown (Informal)
[Evaluating Automatic Speech Recognition Quality and Its Impact on Counselor Utterance Coding](https://aclanthology.org/2021.clpsych-1.18) (Min et al., CLPsych 2021)
ACL