Spontaneous speech recognition using a statistical coarticulatory model for the vocal-tract-resonance dynamics.

By Li Deng, Jeff Z. Ma, N. Ontario. 2000

93 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Experimental and Cognitive Psychology, Signal Processing

How researchers see this paper

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

In Artificial Intelligence

1. Li Deng
2. Dong Yu
3. Ossama Abdel-Hamid
4. Jinyu Li
5. Zhenhua Ling
6. Jianfeng Gao
7. Yoshua Bengio
8. Xiaodong He

In Experimental and Cognitive Psychology

1. Dong Yu
2. Li Deng
3. Zhenhua Ling
4. Jeff Z. Ma

In Signal Processing

1. Li Deng
2. Dong Yu
3. Ossama Abdel-Hamid
4. Jinyu Li
5. Zhenhua Ling
6. Yifan Gong
7. Frank Torsten Bernd Seide
8. S. Renals

Citations in the corpus

• Deep Learning: Methods and Applications (2014, background): “Subsequent work added a new hidden layer into the dynamic model to explicitly account for the target-directed, articulatory-like properties in human speech generation [45, 73, 74, 83, 96, 75, 90, 231, 232, 233, 251, 282].”
• A tutorial survey of architectures, algorithms, and applications for deep learning (2014, neutral): “In one implementation, lt took the form of shallow MLP weights [69, 163, 164].”
• Target-directed mixture dynamic models for spontaneous speech recognition (2004, background): “During our earlier work [4], [10], we found that the nonlinear function represented by the MLP had not provided an accurate nonlinear mapping relationship between the VTR and the MFCC spaces.”
• Efficient decoding strategies for conversational speech recognition using a constrained nonlinear state-space model (2003, methodology): “(They are both automatically estimated using the EM algorithm as presented in [12].) is an additive, zero-mean, Gaussian i.i.d. " state " noise with covariance matrix .”
• A deep convolutional neural network using heterogeneous pooling for trading acoustic invariance with phonetic confusion (2013, background): “frequency changes [10][11] --- associated with the same speech”
• Modeling Spectral Envelopes Using Restricted Boltzmann Machines and Deep Belief Networks for Statistical Parametric Speech Synthesis (2013, methodology): “The architectures used in deep learning as applied to speech processing have been motivated by the multi-layered structures in both speech production and perception involving phonological features, motor control, articulatory dynamics, and acoustic and auditory parameters [26], [27].”