Speech trajectory discrimination using the minimum classification error learning

By R. Chengalvarayan, Li Deng. 1998

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Li Deng
2. Dong Yu
3. Xiaodong He
4. Yoshua Bengio
5. Jianfeng Gao
6. Trevor Darrell
7. Kristen Grauman
8. Zhe Gan

Citations in the corpus

• Deep Learning: Methods and Applications (2014, methodology): “Many of the discriminative techniques for supervised learning in signal and information processing are shallow architectures such as HMMs [52, 127, 147, 186, 188, 290, 394, 418] and conditional random fields (CRFs) [151, 155, 281, 400, 429, 446].”
• Machine Learning Paradigms for Speech Recognition: An Overview (2013, background): “The early work in the area can be found in [128], where MCE is used to discriminatively learn all the polynomial coefficients in the trajectory model discussed in Section III.”
• Discriminative learning in sequential pattern recognition (2008, background): “[61]; 2) minimum classification error (MCE) [1], [9], [23], [28], [29], [35], [36], [38], [49], [52], [54]; and 3) minimum phone error (MPE) and closely related minimum word error (MWE) [13], [45]–[48].”
• Bhattacharyya and Expected Likelihood Kernels (2003, background): “For instance, a generative model may be estimated conditionally [5, 3, 21] or discriminatively [11, 23] to improve its performance for classification.”