COM 发表于 2025-3-23 10:31:41

Experimental Systemsvanced Technologies (Denver, CO), and more recently with Michael Cohen, Horacio Franco, and Victor Abrash of SRI (Stanford, CA). The results of this continuing work are presented here to show that the hybrid HMM/MLP approach can improve state-of-the-art large vocabulary, continuous speech recognition systems.

失败主义者 发表于 2025-3-23 17:14:23

Context-Dependent MLPs, current state-of-the-art continuous speech recognizers require HMMs with greater complexity, e.g., multiple densities per phone and/or context-dependent phone models. Will the consistent improvement we have seen in these tests be washed out in systems with more detailed models?

寻找 发表于 2025-3-23 20:30:08

HMM/MLP and Predictive Modelsability that a particular acoustic vector is emitted at a given time only depends on the current state and the current acoustic vector. As a consequence, this model does not take account of the dynamic nature of the speech signal..

Focus-Words 发表于 2025-3-23 23:43:57

http://reply.papertrans.cn/24/2357/235622/235622_14.png

嫌恶 发表于 2025-3-24 03:58:44

Statistical Thermodynamics of Turbulence,ckson, 1990; Hertz, Krogh, & Palmer, 1991; Zu-rada, 1992]. For more information on learning algorithms, performance evaluation, and applications, see . For more references and application areas, see .

insomnia 发表于 2025-3-24 08:30:11

http://reply.papertrans.cn/24/2357/235622/235622_16.png

perimenopause 发表于 2025-3-24 12:11:03

http://reply.papertrans.cn/24/2357/235622/235622_17.png

LATER 发表于 2025-3-24 16:16:44

0893-3405 ches 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 emissionp

hurricane 发表于 2025-3-24 20:39:33

http://reply.papertrans.cn/24/2357/235622/235622_19.png

auxiliary 发表于 2025-3-24 23:34:05

http://reply.papertrans.cn/24/2357/235622/235622_20.png
页: 1 [2] 3 4 5 6 7
查看完整版本: Titlebook: Connectionist Speech Recognition; A Hybrid Approach Hervé A. Bourlard,Nelson Morgan Book 1994 Springer Science+Business Media New York 1994