Modeling the effect of linguistic predictability on speech intelligibility prediction.
Modeling the effect of linguistic predictability on speech intelligibility prediction.
复制标题
DOI:
10.1121/10.0017648
复制
发表时间:
2023-03
影响因子:
1
通讯作者:
Jensen, Jesper
中科院分区:
文献类型:
--
作者:
Edraki, Amin;Chan, Wai-Yip;Fogerty, Daniel;Jensen, Jesper
Many existing speech intelligibility prediction (SIP) algorithms can only account for acoustic factors affecting speech intelligibility and cannot predict intelligibility across corpora with different linguistic predictability. To address this, a linguistic component was added to five existing SIP algorithms by estimating linguistic corpus predictability using a pre-trained language model. The results showed improved SIP performance in terms of correlation and prediction error over a mixture of four datasets, each with a different English open-set corpus.
登录
查看更多内容
影响因子:
2.4
作者:
Fogerty, Daniel;Entwistle, Jenine L.
通讯作者:
Entwistle, Jenine L.
影响因子:
3.2
作者:
Goldwater, Sharon;Jurafsky, Dan;Manning, Christopher D.
通讯作者:
Manning, Christopher D.
影响因子:
--
作者:
MILLER, GA;HEISE, GA;LICHTEN, W
通讯作者:
LICHTEN, W
DOI:
10.1109/taslp.2022.3184888
发表时间:
2022
影响因子:
5.4
作者:
Karbasi, Mahdie;Zeiler, Steffen;Kolossa, Dorothea
通讯作者:
Kolossa, Dorothea
影响因子:
2.5
作者:
Frank, Stefan L.;Otten, Leun J.;Vigliocco, Gabriella
通讯作者:
Vigliocco, Gabriella