Name
Title | ||
|---|---|---|
Building Acoustic Model Ensembles by Data Sampling With Enhanced Trainings and Features |
Abstract | ||
|---|---|---|
We propose a novel approach of using Cross Validation (CV) and Speaker Clustering (SC) based data samplings to construct an ensemble of acoustic models for speech recognition. We also investigate the effects of the existing techniques of Cross Validation Expectation Maximization (CVEM), Discriminative Training (DT), and Multiple Layer Perceptron (MLP) features on the quality of the proposed ensemble acoustic models (EAMs). We have evaluated the proposed methods on TIMIT phoneme recognition task as well as on a telemedicine automatic captioning task. The proposed methods have led to significant improvements in recognition accuracy over conventional Hidden Markov Model (HMM) baseline systems, and the integration of EAMs with CVEM, DT, and MLP has also significantly improved the accuracy performances of the single model systems based on CVEM, DT, and MLP, where the increased inter-model diversity is shown to have played an important role in the performance gain. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/TASL.2012.2227729 | IEEE Transactions on Audio, Speech, and Language Processing |
Keywords | Field | DocType |
telemedicine automatic captioning task,recognition accuracy,multiple layer perceptron,expectation-maximisation algorithm,pattern clustering,timit phoneme recognition task,cvem,signal sampling,cross validation expectation maximization,dt,speech recognition,mlp feature,sc,eam,multilayer perceptrons,speaker recognition,discriminative training,acoustic signal processing,hidden markov model,data sampling,mlp,ensemble acoustic model,speaker clustering,intermodel diversity,hidden markov models,cross validation data sampling,hmm baseline system,speaker clustering data sampling,acoustics,computational modeling,data models | TIMIT,Pattern recognition,Computer science,Speech recognition,Speaker recognition,Artificial intelligence,Cluster analysis,Hidden Markov model,Cross-validation,Discriminative model,Perceptron,Acoustic model | Journal |
Volume | Issue | ISSN |
21 | 3 | 1558-7916 |
Citations | PageRank | References |
7 | 0.48 | 19 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xin Chen | 1 | 116 | 9.64 |
| Yunxin Zhao | 2 | 807 | 121.74 |