广口瓶
发表于 2025-3-25 06:14:11
http://reply.papertrans.cn/29/2813/281227/281227_21.png
爱了吗
发表于 2025-3-25 10:13:04
Discriminative Learning: A Unified objective Function,HMMs). These are: maximum mutual information (MMI), minimum classification error (MCE), and minimum phone error/minimum word error (MPE/MWE). We also compare our unified form of these objective functions with another popular unified form in the literature.
meretricious
发表于 2025-3-25 14:39:03
Discriminative Learning Algorithm for Exponential-Family Distributions,design where each class is characterized by an exponential-family distribution discussed in Chapter 1. The next chapter extends the results here into the more difficult but practically more useful case of hidden Markov models (HMMs).
Proclaim
发表于 2025-3-25 17:03:56
http://reply.papertrans.cn/29/2813/281227/281227_24.png
FAR
发表于 2025-3-25 20:18:27
http://reply.papertrans.cn/29/2813/281227/281227_25.png
Subdue
发表于 2025-3-26 03:17:26
1932-121X ech recognition. The specific models treated in depth include the widely used exponential-family distributions and the hidden Markov model. A detailed study is presented on unifying the common objective functions for discriminative learning in speech recognition, namely maximum mutual information (M
星球的光亮度
发表于 2025-3-26 04:26:13
CSR, Sustainability, Ethics & Governancey, real-world speech recognition tasks such as commercial telephony large-vocabulary ASR (LV-ASR) applications. We show that the GT-based discriminative training gives superior performance over the conventional maximum likelihood (ML)-based training method.
啤酒
发表于 2025-3-26 12:03:41
http://reply.papertrans.cn/29/2813/281227/281227_28.png
NUL
发表于 2025-3-26 14:59:19
Book 2008ition. The specific models treated in depth include the widely used exponential-family distributions and the hidden Markov model. A detailed study is presented on unifying the common objective functions for discriminative learning in speech recognition, namely maximum mutual information (MMI), minim
感染
发表于 2025-3-26 18:39:01
http://reply.papertrans.cn/29/2813/281227/281227_30.png