@inproceedings{clifton-etal-2020-100000,
title = "100,000 Podcasts: A Spoken {E}nglish Document Corpus",
author = "Clifton, Ann and
Reddy, Sravana and
Yu, Yongze and
Pappu, Aasish and
Rezapour, Rezvaneh and
Bonab, Hamed and
Eskevich, Maria and
Jones, Gareth and
Karlgren, Jussi and
Carterette, Ben and
Jones, Rosie",
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.519",
doi = "10.18653/v1/2020.coling-main.519",
pages = "5903--5917",
abstract = "Podcasts are a large and growing repository of spoken audio. As an audio format, podcasts are more varied in style and production type than broadcast news, contain more genres than typically studied in video data, and are more varied in style and format than previous corpora of conversations. When transcribed with automatic speech recognition they represent a noisy but fascinating collection of documents which can be studied through the lens of natural language processing, information retrieval, and linguistics. Paired with the audio files, they are also a resource for speech processing and the study of paralinguistic, sociolinguistic, and acoustic aspects of the domain. We introduce the Spotify Podcast Dataset, a new corpus of 100,000 podcasts. We demonstrate the complexity of the domain with a case study of two tasks: (1) passage search and (2) summarization. This is orders of magnitude larger than previous speech corpora used for search and summarization. Our results show that the size and variability of this corpus opens up new avenues for research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="clifton-etal-2020-100000">
<titleInfo>
<title>100,000 Podcasts: A Spoken English Document Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ann</namePart>
<namePart type="family">Clifton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sravana</namePart>
<namePart type="family">Reddy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongze</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aasish</namePart>
<namePart type="family">Pappu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rezvaneh</namePart>
<namePart type="family">Rezapour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamed</namePart>
<namePart type="family">Bonab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Eskevich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gareth</namePart>
<namePart type="family">Jones</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jussi</namePart>
<namePart type="family">Karlgren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">Carterette</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rosie</namePart>
<namePart type="family">Jones</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>Podcasts are a large and growing repository of spoken audio. As an audio format, podcasts are more varied in style and production type than broadcast news, contain more genres than typically studied in video data, and are more varied in style and format than previous corpora of conversations. When transcribed with automatic speech recognition they represent a noisy but fascinating collection of documents which can be studied through the lens of natural language processing, information retrieval, and linguistics. Paired with the audio files, they are also a resource for speech processing and the study of paralinguistic, sociolinguistic, and acoustic aspects of the domain. We introduce the Spotify Podcast Dataset, a new corpus of 100,000 podcasts. We demonstrate the complexity of the domain with a case study of two tasks: (1) passage search and (2) summarization. This is orders of magnitude larger than previous speech corpora used for search and summarization. Our results show that the size and variability of this corpus opens up new avenues for research.</abstract>
<identifier type="citekey">clifton-etal-2020-100000</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.519</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.519</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>5903</start>
<end>5917</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 100,000 Podcasts: A Spoken English Document Corpus
%A Clifton, Ann
%A Reddy, Sravana
%A Yu, Yongze
%A Pappu, Aasish
%A Rezapour, Rezvaneh
%A Bonab, Hamed
%A Eskevich, Maria
%A Jones, Gareth
%A Karlgren, Jussi
%A Carterette, Ben
%A Jones, Rosie
%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 clifton-etal-2020-100000
%X Podcasts are a large and growing repository of spoken audio. As an audio format, podcasts are more varied in style and production type than broadcast news, contain more genres than typically studied in video data, and are more varied in style and format than previous corpora of conversations. When transcribed with automatic speech recognition they represent a noisy but fascinating collection of documents which can be studied through the lens of natural language processing, information retrieval, and linguistics. Paired with the audio files, they are also a resource for speech processing and the study of paralinguistic, sociolinguistic, and acoustic aspects of the domain. We introduce the Spotify Podcast Dataset, a new corpus of 100,000 podcasts. We demonstrate the complexity of the domain with a case study of two tasks: (1) passage search and (2) summarization. This is orders of magnitude larger than previous speech corpora used for search and summarization. Our results show that the size and variability of this corpus opens up new avenues for research.
%R 10.18653/v1/2020.coling-main.519
%U https://aclanthology.org/2020.coling-main.519
%U https://doi.org/10.18653/v1/2020.coling-main.519
%P 5903-5917
Markdown (Informal)
[100,000 Podcasts: A Spoken English Document Corpus](https://aclanthology.org/2020.coling-main.519) (Clifton et al., COLING 2020)
ACL
- Ann Clifton, Sravana Reddy, Yongze Yu, Aasish Pappu, Rezvaneh Rezapour, Hamed Bonab, Maria Eskevich, Gareth Jones, Jussi Karlgren, Ben Carterette, and Rosie Jones. 2020. 100,000 Podcasts: A Spoken English Document Corpus. In Proceedings of the 28th International Conference on Computational Linguistics, pages 5903–5917, Barcelona, Spain (Online). International Committee on Computational Linguistics.