Abstract | ||
---|---|---|
Due to the distinct search space and efficiency demands in different ASR applications, the state-of-the-art confidence measures and their decoding frameworks are heterogeneous among keyword spotting, domain-specific recognition and LVCSR. Inspired by the success in applying a phone level language model to replace the word lattice in discriminative training, the auxiliary normalization graph is proposed in this work, and it is constructed to model the observation probability in hypothesis posterior based confidence measure. In this way, confidence measure normalizing term modelling can be independent from the original search space and the confidence measure can be grouped into an unified framework. Experiments on three typical ASR applications show that the proposed method using a unified confidence measure framework achieves comparable performance to the separately optimized system on each task. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1007/978-3-319-67777-4_11 | INTELLIGENCE SCIENCE AND BIG DATA ENGINEERING, ISCIDE 2017 |
Keywords | Field | DocType |
Confidence measure, Auxiliary normalization graph, Connectionist temporal classification, Phone synchronous decoding | Confidence measures,Graph,Normalization (statistics),Pattern recognition,Computer science,Keyword spotting,Phone,Artificial intelligence,Decoding methods,Discriminative model,Language model | Conference |
Volume | ISSN | Citations |
10559 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 10 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhehuai Chen | 1 | 11 | 3.89 |
Yanmin Qian | 2 | 295 | 44.44 |
Kai Yu | 3 | 1082 | 90.58 |