Abstract | ||
---|---|---|
This paper describes the combination of two recent machine learning techniques for acoustic modeling in speech recognition: deep neural networks (DNNs) and graph-based semi-supervised learning (SSL). While DNNs have been shown to be powerful supervised classifiers and have achieved considerable success in speech recognition, graph-based SSL can exploit valuable complementary information derived from the manifold structure of the unlabeled test data. Previous work on graph-based SSL in acoustic modeling has been limited to frame-level classification tasks and has not been compared to, or integrated with, state-of-the-art DNN/HMM recognizers. This paper represents the first integration of graph-based SSL with DNN based speech recognition and analyzes its effect on word recognition performance. The approach is evaluated on two small vocabulary speech recognition tasks and shows a significant improvement in HMM state classification accuracy as well as a consistent reduction in word error rate over a state-of-the-art DNN/HMM baseline. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/SLT.2014.7078570 | SLT |
Keywords | Field | DocType |
hmm state classification accuracy,acoustic modeling,deep neural networks,graph-based semisupervised acoustic modeling,speech recognition,word recognition performance,graph-based semisupervised learning,learning (artificial intelligence),pattern classification,unlabeled test data,semi-supervised learning,supervised classifiers,machine learning techniques,frame-level classification tasks,graph theory,graph-based ssl,dnn-based speech recognition,small vocabulary speech recognition tasks,graph-based learning,hidden markov models,neural nets,semi supervised learning | Graph,Semi-supervised learning,Pattern recognition,Computer science,Word error rate,Word recognition,Exploit,Speech recognition,Test data,Artificial intelligence,Hidden Markov model,Deep neural networks | Conference |
ISSN | Citations | PageRank |
2639-5479 | 5 | 0.41 |
References | Authors | |
17 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yuzong Liu | 1 | 96 | 6.63 |
Katrin Kirchhoff | 2 | 1026 | 95.24 |