| 书目名称 | Connectionist Speech Recognition |
| 副标题 | A Hybrid Approach |
| 编辑 | Hervé A. Bourlard,Nelson Morgan |
| 视频video | http://file.papertrans.cn/236/235622/235622.mp4 |
| 丛书名称 | The Springer International Series in Engineering and Computer Science |
| 图书封面 |  |
| 描述 | .Connectionist Speech Recognition: A Hybrid Approach.describes the theory and implementation of a method to incorporateneural network approaches into state of the art continuous speechrecognition systems based on hidden Markov models (HMMs) to improvetheir performance. In this framework, neural networks (and inparticular, multilayer perceptrons or MLPs) have been restricted towell-defined subtasks of the whole system, i.e. HMM emissionprobability estimation and feature extraction. .The book describes a successful five-year international collaborationbetween the authors. The lessons learned form a case study thatdemonstrates how hybrid systems can be developed to combine neuralnetworks with more traditional statistical approaches. The bookillustrates both the advantages and limitations of neural networks inthe framework of a statistical systems. .Using standard databases and comparison with some conventionalapproaches, it is shown that MLP probability estimation can improverecognition performance. Other approaches are discussed, though thereis no such unequivocal experimental result for these methods. ..Connectionist Speech Recognition. is of use to anyone intendingto use neural net |
| 出版日期 | Book 1994 |
| 关键词 | Hardware; Markov model; Software; Standard; artificial intelligence; classification; development; hidden ma |
| 版次 | 1 |
| doi | https://doi.org/10.1007/978-1-4615-3210-1 |
| isbn_softcover | 978-1-4613-6409-2 |
| isbn_ebook | 978-1-4615-3210-1Series ISSN 0893-3405 |
| issn_series | 0893-3405 |
| copyright | Springer Science+Business Media New York 1994 |
|Archiver|手机版|小黑屋|
派博传思国际
( 京公网安备110108008328)
GMT+8, 2025-11-16 21:07
发表于 2025-3-21 18:02:54
