Publication detail

Evaluating the Santa Barbara Corpus: Challenges of the Breadth of Conversational Spoken Language

MACIEJEWSKI, M. KLEMENT, D. HUANG, R. WIESNER, M. KHUDANPUR, S.

Original Title

Evaluating the Santa Barbara Corpus: Challenges of the Breadth of Conversational Spoken Language

Type

conference paper

Language

English

Original Abstract

As speech technology has matured, there has been a push to- wards systems that can process conversational speech, reflect- ing the so-called "cocktail party problem," which includes not only more challenging acoustic conditions, but also necessi- tates solutions to new problems, such as identifying who spoke when and processing multiple concurrent streams of speech. Such problems have been approached primarily via corpora comprising business meetings and dinner parties, overlooking the broad range of conversational dynamics and speaker de- mographics that fall under the category of multi-talker speech. To this end, we introduce the use of the Santa Barbara Corpus of Spoken American English for evaluation of speech technol- ogy-including preparing the corpus and annotations for auto- matic processing, demonstrating the failure of state-of-the-art systems to withstand the heterogeneity of conditions, and high- lighting the situations where standard methods struggle to per- form at all

Keywords

conversational speech, diarization, speech recognition

Authors

MACIEJEWSKI, M.; KLEMENT, D.; HUANG, R.; WIESNER, M.; KHUDANPUR, S.

Released

1. 9. 2024

Publisher

International Speech Communication Association

Location

Kos

ISBN

1990-9772

Periodical

Proceedings of Interspeech

Year of study

2024

Number

9

State

French Republic

Pages from

2155

Pages to

2160

Pages count

5

URL

https://www.isca-archive.org/interspeech_2024/maciejewski24_interspeech.pdf

BibTex

@inproceedings{BUT193741,
  author="MACIEJEWSKI, M. and KLEMENT, D. and HUANG, R. and WIESNER, M. and KHUDANPUR, S.",
  title="Evaluating the Santa Barbara Corpus: Challenges of the Breadth of Conversational Spoken Language",
  booktitle="Proceedings of Interspeech 2024",
  year="2024",
  journal="Proceedings of Interspeech",
  volume="2024",
  number="9",
  pages="2155--2160",
  publisher="International Speech Communication Association",
  address="Kos",
  doi="10.21437/Interspeech.2024-2119",
  issn="1990-9772",
  url="https://www.isca-archive.org/interspeech_2024/maciejewski24_interspeech.pdf"
}

Documents

maciejewski_2024_interspeech.pdf