Please use this identifier to cite or link to this item:
|Title:||Semi-parametric trajectory modelling using temporally varying feature mapping for speech recognition|
|Authors:||Sim, K.C. |
Conditional random field
|Citation:||Sim, K.C.,Liu, S. (2010). Semi-parametric trajectory modelling using temporally varying feature mapping for speech recognition. Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010 : 2982-2985. ScholarBank@NUS Repository.|
|Abstract:||Recently, trajectory HMM has been shown to improve the performance of both speech recognition and speech synthesis. For efficiency, state sequence is required to compute likelihood for trajectory HMM which limits its use to N-best rescoring for speech recognition. Motivated by the success of models with temporally varying parameters, this paper proposes a Temporally Varying Feature Mapping (TVFM) model to transform the feature vector sequence such that the trajectory information as modelled by trajectory HMM is suppressed. Therefore, TVFM can be perceived as an implicit trajectory modelling technique. Two approaches for estimating the TVFM parameters are presented. Experimental results for phone recognition on TIMIT and word recognition on Wall Street Journal show that promising results can be obtained using TVFM. © 2010 ISCA.|
|Source Title:||Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Jan 13, 2019
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.