Publications
Detailed Information
An HMM-MLP hybrid approach for improving discrimination in speech recognition
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Na, Kyungmin | - |
dc.contributor.author | Chae, Soo-Ik | - |
dc.date.accessioned | 2009-12-18T05:57:25Z | - |
dc.date.available | 2009-12-18T05:57:25Z | - |
dc.date.issued | 1998-05 | - |
dc.identifier.citation | Proceedings of the International Joint Conference on Neural Networks, pp.156-159 | en |
dc.identifier.uri | https://hdl.handle.net/10371/21380 | - |
dc.description.abstract | In this paper, we propose an HMMZMLP hybrid scheme
for achieving high discrimination in speech recognition. Io the conventional hybrid approaches, an MLP is trained as a distribution estimator or as a VQ labeler, and the HMMs pegonn recognition using the output of the MLP, In the proposed method, to the contrary, HMMs generate a new feature vector of a fixed dimension by concatenating their state log-likelihoods, and an MLP discriminator pegoms recognition by using this new feature vector as an input. The proposed method was tested on the nine American E-set letters from the ISOLET database of the OGI. For comparison, a weighted HMM VHMM) algorithm and GPD-based WHMM algorithm which use an adaptively-trained linear discriminator were also tested. In most cases, the recognition rates on the closed-test and open-test sets of the proposed method were higher than those of the conventional methods. | en |
dc.language.iso | en | - |
dc.title | An HMM-MLP hybrid approach for improving discrimination in speech recognition | en |
dc.type | Conference Paper | en |
dc.contributor.AlternativeAuthor | 나경민 | - |
dc.contributor.AlternativeAuthor | 채수익 | - |
- Appears in Collections:
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.