Name
Abstract | ||
|---|---|---|
This paper presents a method to automatically quantify the spoken English fluency skills of speakers. The focus of this work is to automatically compute a numeric score of spoken fluency that is correlated with the numerical score the human assessors would assign. The proposed method combines several novel prosodic and lexical features to compute the fluency score. It is shown that the prosodic and the lexical features provide complementary information for fluency evaluation. Extensive evaluation on human-labeled utterances shows that the proposed technique exhibits similar trends in performance and confusions as shown by human assessors. The proposed technique leads to 84.2% classification accuracy when the two extreme classes of fluency are considered. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/ICASSP.2009.4960712 | ICASSP |
Keywords | Field | DocType |
natural language processing,speech processing,fluency evaluation,fluency score,human assessors,human-labeled utterances,language learning,lexical features,numerical score,spoken English fluency,fluency evaluation,language learning,lexical features,prosodic features | Signal processing,Speech processing,Fluency,Computer science,Usability,Feature extraction,Speech recognition,Language acquisition,Natural language,Artificial intelligence,Natural language processing | Conference |
ISSN | Citations | PageRank |
1520-6149 | 3 | 0.56 |
References | Authors | |
6 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Om Deshmukh | 1 | 25 | 2.97 |
| Kundan Kandhway | 2 | 68 | 7.30 |
| Ashish Verma | 3 | 17 | 2.39 |
| Kartik Audhkhasi | 4 | 189 | 23.25 |