Abstract | ||
---|---|---|
Articulatory precision is a critical factor that influences speaker intelligibility. In this letter, we propose a new measure we call “articulation entropy” that serves as a proxy for the number of distinct phonemes a person produces when he or she speaks. The method is based on the observation that the ability of a speaker to achieve an articulatory target, and hence clearly produce distinct phon... |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/LSP.2016.2633871 | IEEE Signal Processing Letters |
Keywords | Field | DocType |
Speech,Entropy,Feature extraction,Estimation,Acoustics,Acoustic measurements,Databases | Neurological impairment,Data set,Pattern recognition,Computer science,Segmentation,Speech recognition,Artificial intelligence,Formant,Mandarin Chinese,Intelligibility (communication) | Journal |
Volume | Issue | ISSN |
24 | 4 | 1070-9908 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yishan Jiao | 1 | 10 | 2.61 |
Visar Berisha | 2 | 76 | 22.38 |
Julie Liss | 3 | 0 | 0.68 |
Sih-Chiao Hsu | 4 | 0 | 0.34 |
Erika S. Levy | 5 | 2 | 1.41 |
Megan McAuliffe | 6 | 0 | 0.34 |