Title | ||
---|---|---|
Building an ensemble of CD-DNN-HMM acoustic model using random forests of phonetic decision trees |
Abstract | ||
---|---|---|
We propose an RF-PDT+CD-DNN approach to generate an ensemble of context-dependent pre-trained deep neural networks (CD-DNNs) using random forests of phonetic decision trees (RF-PDTs) and constructing a CD-DNN-HMM-based ensemble acoustic model (EAM). We present evaluation results on the TIMIT dataset and a telemedicine automatic captioning dataset and demonstrate that the proposed RF-PDT+CD-DNN based EAM significantly outperforms the CD-DNN based single acoustic model (SAM) in phone and word recognition accuracies. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/ISCSLP.2014.6936680 | ISCSLP |
Keywords | Field | DocType |
deep neural network,random forest,telemedicine automatic captioning dataset,phone recognition accuracies,sam,speech recognition,telemedicine,timit dataset,eam,random forests,word recognition accuracies,discriminative pre-training,phonetic decision trees,context-dependent pretrained deep neural networks,cd-dnn-hmm acoustic model ensemble,ensemble acoustic model,single acoustic model,decision trees,neural nets,rf-pdt+cd-dnn,random forests of phonetic decision trees,phonetic decision tree | TIMIT,Decision tree,Closed captioning,Pattern recognition,Computer science,Word recognition,Speech recognition,Phone,Artificial intelligence,Random forest,Hidden Markov model,Acoustic model | Conference |
Citations | PageRank | References |
4 | 0.40 | 11 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tuo Zhao | 1 | 222 | 40.58 |
Yunxin Zhao | 2 | 807 | 121.74 |
Xin Chen | 3 | 116 | 9.64 |