@inproceedings{huang-etal-2024-conec,
title = "{C}on{EC}: Earnings Call Dataset with Real-world Contexts for Benchmarking Contextual Speech Recognition",
author = "Huang, Ruizhe and
Yarmohammadi, Mahsa and
Trmal, Jan and
Liu, Jing and
Raj, Desh and
Garcia, Leibny Paola and
Ivanov, Alexei V. and
Ehlen, Patrick and
Yu, Mingzhi and
Povey, Dan and
Khudanpur, Sanjeev",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.328",
pages = "3700--3706",
abstract = "Knowing the particular context associated with a conversation can help improving the performance of an automatic speech recognition (ASR) system. For example, if we are provided with a list of in-context words or phrases {---} such as the speaker{'}s contacts or recent song playlists {---} during inference, we can bias the recognition process towards this list. There are many works addressing contextual ASR; however, there is few publicly available real benchmark for evaluation, making it difficult to compare different solutions. To this end, we provide a corpus ({``}ConEC{''}) and baselines to evaluate contextual ASR approaches, grounded on real-world applications. The ConEC corpus is based on public-domain earnings calls (ECs) and associated supplementary materials, such as presentation slides, earnings news release as well as a list of meeting participants{'} names and affiliations. We demonstrate that such real contexts are noisier than artificially synthesized contexts that contain the ground truth, yet they still make great room for future improvement of contextual ASR technology",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2024-conec">
<titleInfo>
<title>ConEC: Earnings Call Dataset with Real-world Contexts for Benchmarking Contextual Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruizhe</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahsa</namePart>
<namePart type="family">Yarmohammadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Trmal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desh</namePart>
<namePart type="family">Raj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leibny</namePart>
<namePart type="given">Paola</namePart>
<namePart type="family">Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexei</namePart>
<namePart type="given">V</namePart>
<namePart type="family">Ivanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Ehlen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingzhi</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Povey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanjeev</namePart>
<namePart type="family">Khudanpur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Knowing the particular context associated with a conversation can help improving the performance of an automatic speech recognition (ASR) system. For example, if we are provided with a list of in-context words or phrases — such as the speaker’s contacts or recent song playlists — during inference, we can bias the recognition process towards this list. There are many works addressing contextual ASR; however, there is few publicly available real benchmark for evaluation, making it difficult to compare different solutions. To this end, we provide a corpus (“ConEC”) and baselines to evaluate contextual ASR approaches, grounded on real-world applications. The ConEC corpus is based on public-domain earnings calls (ECs) and associated supplementary materials, such as presentation slides, earnings news release as well as a list of meeting participants’ names and affiliations. We demonstrate that such real contexts are noisier than artificially synthesized contexts that contain the ground truth, yet they still make great room for future improvement of contextual ASR technology</abstract>
<identifier type="citekey">huang-etal-2024-conec</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.328</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>3700</start>
<end>3706</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ConEC: Earnings Call Dataset with Real-world Contexts for Benchmarking Contextual Speech Recognition
%A Huang, Ruizhe
%A Yarmohammadi, Mahsa
%A Trmal, Jan
%A Liu, Jing
%A Raj, Desh
%A Garcia, Leibny Paola
%A Ivanov, Alexei V.
%A Ehlen, Patrick
%A Yu, Mingzhi
%A Povey, Dan
%A Khudanpur, Sanjeev
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F huang-etal-2024-conec
%X Knowing the particular context associated with a conversation can help improving the performance of an automatic speech recognition (ASR) system. For example, if we are provided with a list of in-context words or phrases — such as the speaker’s contacts or recent song playlists — during inference, we can bias the recognition process towards this list. There are many works addressing contextual ASR; however, there is few publicly available real benchmark for evaluation, making it difficult to compare different solutions. To this end, we provide a corpus (“ConEC”) and baselines to evaluate contextual ASR approaches, grounded on real-world applications. The ConEC corpus is based on public-domain earnings calls (ECs) and associated supplementary materials, such as presentation slides, earnings news release as well as a list of meeting participants’ names and affiliations. We demonstrate that such real contexts are noisier than artificially synthesized contexts that contain the ground truth, yet they still make great room for future improvement of contextual ASR technology
%U https://aclanthology.org/2024.lrec-main.328
%P 3700-3706
Markdown (Informal)
[ConEC: Earnings Call Dataset with Real-world Contexts for Benchmarking Contextual Speech Recognition](https://aclanthology.org/2024.lrec-main.328) (Huang et al., LREC-COLING 2024)
ACL
- Ruizhe Huang, Mahsa Yarmohammadi, Jan Trmal, Jing Liu, Desh Raj, Leibny Paola Garcia, Alexei V. Ivanov, Patrick Ehlen, Mingzhi Yu, Dan Povey, and Sanjeev Khudanpur. 2024. ConEC: Earnings Call Dataset with Real-world Contexts for Benchmarking Contextual Speech Recognition. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 3700–3706, Torino, Italia. ELRA and ICCL.