Boosting attribute and phone estimation accuracies with deep neural networks for detection-based speech recognition

By Dong Yu, Sabato Marco Siniscalchi, Li Deng, Chin-Hui Lee. 2012

76 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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. Dong Yu
2. Li Deng
3. Jinyu Li
4. Yoshua Bengio
5. Tara N. Sainath
6. Quoc V. Le
7. James R. Glass
8. Jianfeng Gao

In Signal Processing

1. Dong Yu
2. Li Deng
3. Jinyu Li
4. Tara N. Sainath
5. Andrew W. Senior
6. M. Seltzer
7. Yoshua Bengio
8. Geoffrey E. Hinton

Citations in the corpus

• Composition of Deep and Spiking Neural Networks for Very Low Bit Rate Speech Coding (2016, background): “Phonology (GP) [10], [11], (ii) the Sound Pattern of English (SPE) [12] and (iii) the extended SPE system (eSPE) [13], [14].”
• Exploring how deep neural networks form phonemic categories (2015, background): “This study suggests a possible basis for this confusion pattern, and motivates new directions to reduce confusions among phonemes [23].”
• Deep Neural Networks for Acoustic Modeling in Speech Recognition (2012, methodology): “This level of accuracy for detecting sub-phonetic fundamental speech units may allow a new family of flexible speech recognition and understanding systems that make use of phonological features in the full detection-based framework discussed in [65].”
• Automatic speech recognition for under-resourced languages: A survey (2014, background): “(2013) is well suited for deep neural network architectures for ASR (Yu et al., 2012).”
• Phonological vocoding using artificial neural networks (2015, methodology): “For natural classes of French sounds, we started from pseudophonological feature classification designed for American English [14].”
• Scalable stacking and learning for building deep architectures (2012, background): “Also, the drastic error reduction of speech attribute detection achieved already by using DBN [14] is expected to be again enhanced by DSN (work ongoing).”
• Exploiting deep neural networks for detection-based speech recognition (2013, methodology): “The shallow MLP results obtained using MFCC input features were quoted from [35] and were obtained using a single hidden layer MLP with 800 hidden units.”
• A deep architecture with bilinear modeling of hidden representations: Applications to phonetic recognition (2012, result): “Further, encouraged by our recent results with DNN and DSN in applications of speech understanding [13] and in speech attribute detection [14], we expect greater success with the use of T-DSN in these and other applications.”
• A Review of Deep Learning with Special Emphasis on Architectures, Applications and Recent Trends (2019, methodology): “6: Autoencoder with 3 neurons in hidden layer recognition [62], computer vision [63] where it is used for the training of higher order factorized Boltzmann machine, speech recognition [75], [76], [77] for pretraining DNN, for pretraining of deep convolutional neural network (CNN) [60], [78], [61].”