@inproceedings{addlesee-etal-2020-comprehensive,
title = "A Comprehensive Evaluation of Incremental Speech Recognition and Diarization for Conversational {AI}",
author = "Addlesee, Angus and
Yu, Yanchao and
Eshghi, Arash",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.312",
doi = "10.18653/v1/2020.coling-main.312",
pages = "3492--3503",
abstract = "Automatic Speech Recognition (ASR) systems are increasingly powerful and more accurate, but also more numerous with several options existing currently as a service (e.g. Google, IBM, and Microsoft). Currently the most stringent standards for such systems are set within the context of their use in, and for, Conversational AI technology. These systems are expected to operate incrementally in real-time, be responsive, stable, and robust to the pervasive yet peculiar characteristics of conversational speech such as disfluencies and overlaps. In this paper we evaluate the most popular of such systems with metrics and experiments designed with these standards in mind. We also evaluate the speaker diarization (SD) capabilities of the same systems which will be particularly important for dialogue systems designed to handle multi-party interaction. We found that Microsoft has the leading incremental ASR system which preserves disfluent materials and IBM has the leading incremental SD system in addition to the ASR that is most robust to speech overlaps. Google strikes a balance between the two but none of these systems are yet suitable to reliably handle natural spontaneous conversations in real-time.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="addlesee-etal-2020-comprehensive">
<titleInfo>
<title>A Comprehensive Evaluation of Incremental Speech Recognition and Diarization for Conversational AI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Angus</namePart>
<namePart type="family">Addlesee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanchao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arash</namePart>
<namePart type="family">Eshghi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic Speech Recognition (ASR) systems are increasingly powerful and more accurate, but also more numerous with several options existing currently as a service (e.g. Google, IBM, and Microsoft). Currently the most stringent standards for such systems are set within the context of their use in, and for, Conversational AI technology. These systems are expected to operate incrementally in real-time, be responsive, stable, and robust to the pervasive yet peculiar characteristics of conversational speech such as disfluencies and overlaps. In this paper we evaluate the most popular of such systems with metrics and experiments designed with these standards in mind. We also evaluate the speaker diarization (SD) capabilities of the same systems which will be particularly important for dialogue systems designed to handle multi-party interaction. We found that Microsoft has the leading incremental ASR system which preserves disfluent materials and IBM has the leading incremental SD system in addition to the ASR that is most robust to speech overlaps. Google strikes a balance between the two but none of these systems are yet suitable to reliably handle natural spontaneous conversations in real-time.</abstract>
<identifier type="citekey">addlesee-etal-2020-comprehensive</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.312</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.312</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>3492</start>
<end>3503</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Comprehensive Evaluation of Incremental Speech Recognition and Diarization for Conversational AI
%A Addlesee, Angus
%A Yu, Yanchao
%A Eshghi, Arash
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F addlesee-etal-2020-comprehensive
%X Automatic Speech Recognition (ASR) systems are increasingly powerful and more accurate, but also more numerous with several options existing currently as a service (e.g. Google, IBM, and Microsoft). Currently the most stringent standards for such systems are set within the context of their use in, and for, Conversational AI technology. These systems are expected to operate incrementally in real-time, be responsive, stable, and robust to the pervasive yet peculiar characteristics of conversational speech such as disfluencies and overlaps. In this paper we evaluate the most popular of such systems with metrics and experiments designed with these standards in mind. We also evaluate the speaker diarization (SD) capabilities of the same systems which will be particularly important for dialogue systems designed to handle multi-party interaction. We found that Microsoft has the leading incremental ASR system which preserves disfluent materials and IBM has the leading incremental SD system in addition to the ASR that is most robust to speech overlaps. Google strikes a balance between the two but none of these systems are yet suitable to reliably handle natural spontaneous conversations in real-time.
%R 10.18653/v1/2020.coling-main.312
%U https://aclanthology.org/2020.coling-main.312
%U https://doi.org/10.18653/v1/2020.coling-main.312
%P 3492-3503
Markdown (Informal)
[A Comprehensive Evaluation of Incremental Speech Recognition and Diarization for Conversational AI](https://aclanthology.org/2020.coling-main.312) (Addlesee et al., COLING 2020)
ACL