Pronunciation Modeling is a computational framework within speech recognition that specifies how linguistic units are mapped to their phonetic realizations, distinguishing itself by accounting for variations in pronunciation due to context, speaker, or dialect.
503
Publications
21.4K
Citations
1.1K
Authors
331
Institutions
Publications per year
2017–2026
67
Publications
503
Parallel Networks that Learn to Pronounce English Text
Terrence J. Sejnowski · 1987 · 1.6K citations
A computational learning model for metrical phonology
B. Elan Dresher, Jonathan D. Kaye · Cognition · 1990 · 357 citations
1–5 of 503
Authors
1.1K
- KLKaren Livescu
Toyota Technological Institute at Chicago, United States
11 publications · 454 citations
11
h-index
- JG
11
h-index
- TK
10
h-index
- HS
10
h-index
- SK
10
h-index
1–5 of 1.1K
Institutions
331
Carnegie Mellon University
Pittsburgh, United States
17 h-index
41 publications
4.2K citations
Johns Hopkins University
Baltimore, United States
15 h-index
46 publications
2.2K citations
Massachusetts Institute of Technology
Cambridge, United States
13 h-index
44 publications
1.1K citations
Radboud University Nijmegen
Nijmegen, The Netherlands
11 h-index
22 publications
1.2K citations
University of Cambridge
Cambridge, United Kingdom
11 h-index
22 publications
897 citations
Chinese University of Hong Kong
Hong Kong, Hong Kong
10 h-index
20 publications
523 citations
SRI International
Menlo Park, United States
10 h-index
27 publications
733 citations
University of Edinburgh
Edinburgh, United Kingdom
9 h-index
27 publications
736 citations
1–8 of 331
Venues
- Speech Communication
22 publications · 1.5K citations
19
h-index
- Computer Speech & Language
13 publications · 587 citations
12
h-index
- IEEE Transactions on Speech and Audio Processing
10 publications · 379 citations
10
h-index
- International Journal of Speech Technology
9 publications · 295 citations
9
h-index
- IEEE Transactions on Audio Speech and Language Processing
9 publications · 259 citations
9
h-index
1–5