| HMM |
| |
- Classification:Numerical Algorithm-Artificial Intelligence - Speech-Voice recognition/combine
- Development Tool:matlab
- Sise:37.0 KB
- Upload time:2012/7/12 3:28:26
- Uploader:briohu
- Download Statistics:
|
| Description |
Implement a Markov model and yin, are a few examples, additional files, HMM speech recognition and can be used to complete source code can be used directly.
File list:
HMM
..\Examples
..\........\fixed_lag_demo.m
..\........\learn_dhmm_demo.m
..\........\learn_mhmm_demo.m
..\........\online_em_demo.m
..\Old
..\...\example1.m
..\...\fixed_lag_smoother.m
..\...\learn_hmm.m
..\...\online_em.m
..\...\online_em_hmm_demo.m
..\...\online_em_pomdp_demo.m
..\...\sample_markov_chain.m
..\approxeq.m
..\consist.m
..\dist2.m
..\em_converged.m
..\enumerate_loglik.m
..\fhmm_infer.m
..\fixed_lag_demo.m
..\fixed_lag_smoother.m
..\forwards.m
..\forwards_backwards.m
..\gaussian_prob.m
..\gmm.m
..\gmminit.m
..\init_mhmm.m
..\kmeans.m
..\learn_dhmm_demo.m
..\learn_hmm.m
..\learn_mhmm.m
..\learn_mhmm_demo.m
..\mk_dhmm_obs_lik.m
..\mk_fhmm_topology.m
..\mk_ghmm_obs_lik.m
..\mk_mhmm_obs_lik.m
..\mk_stochastic.m
..\normalise.m
..\online_em.m
..\online_em_demo.m
..\prob_path.m
..\README
..\sample_dhmm.m
..\sample_discrete.m
..\sample_mc.m
..\sample_mdp.m
..\sample_mhmm.m
..\sample_pomdp.m
..\testfwrite.bin
..\testfwrite.m
..\viterbi_path.m
If you are a member, Log in. If you are not a member, Please register
|
| Related source code |
[ISOLATED_KANNADA_CHARACTER_RECOGNITI...] - Character recognition
[hmm-c] - hmm model of the C language, algorithm refined, suitable for beginners of HMM research.
[hmm-cpp] - HMM model of the C language, algorithm refined, suitable for beginners of HMM research.
[hmmdecode] - here is the code for hmmdecode in matlab
[hmm] - This code contains backward HMM algorithms, Viterbi algorithm and backward algorithm
[HMM-and-mel-feature-extraction] - mel frequency converting and training HMM model
[基于matlab的hmm语音识别] - Hmm speech recognition based on MATLAB
[HMM] - : To make the stress variation in robust speech recognition system to achieve better recognition, research based on hidden Markov models (HMM) adaptive technology, proposed a maximum a posteriori probability (MAP) and the method of maximum likelihood regression (MLLR) for the stress of Adaptive variation in speech. Experimental results show that, compared with the base system, effectively improve the recognition rate of the system in two ways. To SD for the initial models of the maximum posterior probability method to identify best 150 samples of training time, up to 90. 4%.
[hmmtrain] - HMM models, using c language, can be used to pattern recognition source code integrity, and can be used directly.
[HMM1] - Speech recognition training programs, simple and practical. Written in c. Full source code using hidden Markov model has been tested and can be used directly.
|
| Download Address |
 DownLoad
|
| Comments: Don't forget to comment after downloading! Comment... |
|
