Large vocabulary word recognition using context-dependent allophonic hidden Markov models☆

By Li Deng, Matthew Lennig, F. Seitz, P. Mermelstein. 1990

How researchers see this paper

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

1. Jiuxiang Gu
2. Zidong Wang
3. Jianfei Cai
4. Yurong Liu
5. Xiaohui Liu
6. Amir Shahroudy
7. Jun Liu
8. Jason Kuen

Citations in the corpus

• Recent advances in convolutional neural networks (2015, methodology): “Before applying CNN to ASR, this domain has long been dominated by the Hidden Markov Model and Gaussian Mixture Model (GMM-HMM) methods [298, 299] , which usually require extracting hand-craft features on speech signals, e.”
• A survey of deep neural network architectures and their applications (2017, background): “Among them, HMMs and GMMs are widely used for acoustic modeling to generate low-level acoustic contents from high-level acoustic inputs [32,34,79,101,116,120,130].”
• Machine Learning Paradigms for Speech Recognition: An Overview (2013, unknown): “One important innovation in ASR is the introduction of context-dependent states (e.g. [19]), motivated by the desire to reduce output variability associated with each state, a common strategy for " detailed " generative modeling.”
• Design and Learning of Output Representations for Speech Recognition (2013, background): “In 35 almost all state of the art, DNN-based speech recognition systems, the output representation 36 inherits from the over 20-year-old concept of context-dependent (CD) phonetic states [25][15].”