Author | Conference | Journal | Organization | Year | DOI
Look for results that meet for the following criteria:
Academic
Publications
Language identification using a combined articulatory prosody framework

Language identification using a combined articulatory prosody framework,10.1109/ICASSP.2011.5947329,Abhijeet Sangwan,Mahnoosh Mehrabani,John H. L. Han

Edit
Language identification using a combined articulatory prosody framework  
BibTex | RIS | RefWorks Download
This study presents new advancements in our articulatory-based language identi� cation (LID) system. Our LID system automatically identi� es language-features (LFs) from a phonological features (PFs) based representation of speech. While our baseline system uses a static PF-representation for extracting LFs, the new system is based on a dynamic PF representation for feature extraction. Interestingly, the new LFs outperform our baseline system by 11.8% absolute in a dif� cult 5-way classi� cation task of South Indian Languages. Additionally, we incorporate pitch and energy based features in our new system to leverage prosody in classi� cation. In particular, we employ a Legendre polynomial based contour-estimation to capture shape parameters which are used in classi� cation. Additionally, the fusion of PF and prosody-based LFs further improves the overall classi� cation result by 16.5% absolute over the baseline system. Finally, the proposed articulatory language ID system is combined with a PPRLM (parallel phone recognition language model) system to obtain an overall classi� cation accuracy of 86.6%. Index Terms: Language Identi� cation, Articulatory Features, Phonological Features, Prosodical Features
Conference: International Conference on Acoustics, Speech, and Signal Processing - ICASSP , pp. 4400-4403, 2011
Cumulative Annual
View Publication
The following links allow you to view full publications. These links are maintained by other sources not affiliated with Microsoft Academic Search.
Share this on