Home > Research > Publications & Outputs > Segmental Content Effects on Text-dependent Aut...

Research

Associated organisational unit

Electronic data

  • Odyssey2018GB

    Accepted author manuscript, 344 KB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Segmental Content Effects on Text-dependent Automatic Accent Recognition

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Segmental Content Effects on Text-dependent Automatic Accent Recognition. / Brown, Georgina.
Proceedings of Odyssey: The Speaker and Language Recognition Workshop. ISCA, 2018. p. 9-15.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Brown, G 2018, Segmental Content Effects on Text-dependent Automatic Accent Recognition. in Proceedings of Odyssey: The Speaker and Language Recognition Workshop. ISCA, pp. 9-15. https://doi.org/10.21437/Odyssey.2018-2

APA

Brown, G. (2018). Segmental Content Effects on Text-dependent Automatic Accent Recognition. In Proceedings of Odyssey: The Speaker and Language Recognition Workshop (pp. 9-15). ISCA. https://doi.org/10.21437/Odyssey.2018-2

Vancouver

Brown G. Segmental Content Effects on Text-dependent Automatic Accent Recognition. In Proceedings of Odyssey: The Speaker and Language Recognition Workshop. ISCA. 2018. p. 9-15 doi: 10.21437/Odyssey.2018-2

Author

Brown, Georgina. / Segmental Content Effects on Text-dependent Automatic Accent Recognition. Proceedings of Odyssey: The Speaker and Language Recognition Workshop. ISCA, 2018. pp. 9-15

Bibtex

@inproceedings{cee69a8571ab45128ae5917d2c4b021c,
title = "Segmental Content Effects on Text-dependent Automatic Accent Recognition",
abstract = "This paper investigates the effects of an unknown speech sample{\textquoteright}s segmental content (the specific vowels and consonants it contains) on its chances of being successfully classified by an automatic accent recognition system. While there has been some work to investigate this effect in automatic speaker recognition, it has not been explored in relation to automatic accent recognition. This is a task where we would hypothesise that segmental content has a particularly large effect on the likelihood of a successful classification, especially for shorter speech samples. By focussing on one particular text-dependent automatic accent recognition system, the Y-ACCDIST system, we uncover the phonemes that appear to contribute more or less to successful classifications using a corpus of Northern English accents. We also relate these findings to the sociophonetic literature on these specific spoken varieties to attempt to account for the patterns that we see and to consider other factors that might contribute to a sample{\textquoteright}s successful classification.",
author = "Georgina Brown",
year = "2018",
month = jun,
day = "26",
doi = "10.21437/Odyssey.2018-2",
language = "English",
pages = "9--15",
booktitle = "Proceedings of Odyssey: The Speaker and Language Recognition Workshop",
publisher = "ISCA",

}

RIS

TY - GEN

T1 - Segmental Content Effects on Text-dependent Automatic Accent Recognition

AU - Brown, Georgina

PY - 2018/6/26

Y1 - 2018/6/26

N2 - This paper investigates the effects of an unknown speech sample’s segmental content (the specific vowels and consonants it contains) on its chances of being successfully classified by an automatic accent recognition system. While there has been some work to investigate this effect in automatic speaker recognition, it has not been explored in relation to automatic accent recognition. This is a task where we would hypothesise that segmental content has a particularly large effect on the likelihood of a successful classification, especially for shorter speech samples. By focussing on one particular text-dependent automatic accent recognition system, the Y-ACCDIST system, we uncover the phonemes that appear to contribute more or less to successful classifications using a corpus of Northern English accents. We also relate these findings to the sociophonetic literature on these specific spoken varieties to attempt to account for the patterns that we see and to consider other factors that might contribute to a sample’s successful classification.

AB - This paper investigates the effects of an unknown speech sample’s segmental content (the specific vowels and consonants it contains) on its chances of being successfully classified by an automatic accent recognition system. While there has been some work to investigate this effect in automatic speaker recognition, it has not been explored in relation to automatic accent recognition. This is a task where we would hypothesise that segmental content has a particularly large effect on the likelihood of a successful classification, especially for shorter speech samples. By focussing on one particular text-dependent automatic accent recognition system, the Y-ACCDIST system, we uncover the phonemes that appear to contribute more or less to successful classifications using a corpus of Northern English accents. We also relate these findings to the sociophonetic literature on these specific spoken varieties to attempt to account for the patterns that we see and to consider other factors that might contribute to a sample’s successful classification.

U2 - 10.21437/Odyssey.2018-2

DO - 10.21437/Odyssey.2018-2

M3 - Conference contribution/Paper

SP - 9

EP - 15

BT - Proceedings of Odyssey: The Speaker and Language Recognition Workshop

PB - ISCA

ER -