Name
Title | ||
|---|---|---|
Cross-lingual acoustic modeling for Indian languages based on Subspace Gaussian Mixture Models |
Abstract | ||
|---|---|---|
Cross-lingual acoustic modeling using Subspace Gaussian Mixture Model for low-resource languages of Indian origin is investigated. Building acoustic model for a low-resource language with limited vocabulary by leveraging resources from another language with comparatively larger resources was focused upon. Experiments were done on Bengali and Tamil corpus from MANDI database, with Tamil having greater resources than Bengali. We observed that the word accuracy of cross-lingual acoustic model of Bengali was approximately 2.5% above it's CDHMM model and gave equivalent performance as it's monolingual SGMM model. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/NCC.2014.6811282 | NCC |
Keywords | Field | DocType |
gaussian processes,acoustic signal processing,mixture models,speech processing,speech recognition,vocabulary,bengali corpus,cdhmm model,indian languages,mandi database,tamil corpus,cross-lingual acoustic modeling,limited vocabulary,low-resource languages,monolingual sgmm model,subspace gaussian mixture models,cross-lingual acoustic model,sgmm | Subspace Gaussian Mixture Model,Cross lingual,Tamil,Subspace topology,Computer science,Speech recognition,Bengali,Artificial intelligence,Natural language processing,Vocabulary,Mixture model,Acoustic model | Conference |
Citations | PageRank | References |
1 | 0.37 | 8 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Joy, N.M. | 1 | 8 | 2.73 |
| Abraham, B. | 2 | 1 | 0.37 |
| Navneeth, K. | 3 | 1 | 0.37 |
| Srinivasan Umesh | 4 | 93 | 16.31 |