Alert button

"speech recognition": models, code, and papers
Alert button

A segmental framework for fully-unsupervised large-vocabulary speech recognition

Sep 16, 2017
Herman Kamper, Aren Jansen, Sharon Goldwater

Figure 1 for A segmental framework for fully-unsupervised large-vocabulary speech recognition
Figure 2 for A segmental framework for fully-unsupervised large-vocabulary speech recognition
Figure 3 for A segmental framework for fully-unsupervised large-vocabulary speech recognition
Figure 4 for A segmental framework for fully-unsupervised large-vocabulary speech recognition
Viaarxiv icon

Automated Deep Learning: Neural Architecture Search Is Not the End

Dec 16, 2021
Xuanyi Dong, David Jacob Kedziora, Katarzyna Musial, Bogdan Gabrys

Figure 1 for Automated Deep Learning: Neural Architecture Search Is Not the End
Figure 2 for Automated Deep Learning: Neural Architecture Search Is Not the End
Figure 3 for Automated Deep Learning: Neural Architecture Search Is Not the End
Figure 4 for Automated Deep Learning: Neural Architecture Search Is Not the End
Viaarxiv icon

Reducing Exposure Bias in Training Recurrent Neural Network Transducers

Aug 24, 2021
Xiaodong Cui, Brian Kingsbury, George Saon, David Haws, Zoltan Tuske

Figure 1 for Reducing Exposure Bias in Training Recurrent Neural Network Transducers
Figure 2 for Reducing Exposure Bias in Training Recurrent Neural Network Transducers
Figure 3 for Reducing Exposure Bias in Training Recurrent Neural Network Transducers
Figure 4 for Reducing Exposure Bias in Training Recurrent Neural Network Transducers
Viaarxiv icon

Can neural networks predict dynamics they have never seen?

Nov 12, 2021
Anton Pershin, Cedric Beaume, Kuan Li, Steven M. Tobias

Figure 1 for Can neural networks predict dynamics they have never seen?
Figure 2 for Can neural networks predict dynamics they have never seen?
Figure 3 for Can neural networks predict dynamics they have never seen?
Figure 4 for Can neural networks predict dynamics they have never seen?
Viaarxiv icon

Self-Normalized Importance Sampling for Neural Language Modeling

Nov 11, 2021
Zijian Yang, Yingbo Gao, Alexander Gerstenberger, Jintao Jiang, Ralf Schlüter, Hermann Ney

Figure 1 for Self-Normalized Importance Sampling for Neural Language Modeling
Figure 2 for Self-Normalized Importance Sampling for Neural Language Modeling
Figure 3 for Self-Normalized Importance Sampling for Neural Language Modeling
Figure 4 for Self-Normalized Importance Sampling for Neural Language Modeling
Viaarxiv icon

Neural Architecture Search For LF-MMI Trained Time Delay Neural Networks

Jan 12, 2022
Shoukang Hu, Xurong Xie, Mingyu Cui, Jiajun Deng, Shansong Liu, Jianwei Yu, Mengzhe Geng, Xunying Liu, Helen Meng

Figure 1 for Neural Architecture Search For LF-MMI Trained Time Delay Neural Networks
Figure 2 for Neural Architecture Search For LF-MMI Trained Time Delay Neural Networks
Figure 3 for Neural Architecture Search For LF-MMI Trained Time Delay Neural Networks
Figure 4 for Neural Architecture Search For LF-MMI Trained Time Delay Neural Networks
Viaarxiv icon

Common Voice: A Massively-Multilingual Speech Corpus

Dec 13, 2019
Rosana Ardila, Megan Branson, Kelly Davis, Michael Henretty, Michael Kohler, Josh Meyer, Reuben Morais, Lindsay Saunders, Francis M. Tyers, Gregor Weber

Figure 1 for Common Voice: A Massively-Multilingual Speech Corpus
Figure 2 for Common Voice: A Massively-Multilingual Speech Corpus
Figure 3 for Common Voice: A Massively-Multilingual Speech Corpus
Figure 4 for Common Voice: A Massively-Multilingual Speech Corpus
Viaarxiv icon

Temporal Attention Augmented Transformer Hawkes Process

Dec 29, 2021
Lu-ning Zhang, Jian-wei Liu, Zhi-yan Song, Xin Zuo

Figure 1 for Temporal Attention Augmented Transformer Hawkes Process
Figure 2 for Temporal Attention Augmented Transformer Hawkes Process
Figure 3 for Temporal Attention Augmented Transformer Hawkes Process
Figure 4 for Temporal Attention Augmented Transformer Hawkes Process
Viaarxiv icon

ASL Trigger Recognition in Mixed Activity/Signing Sequences for RF Sensor-Based User Interfaces

Nov 10, 2021
Emre Kurtoglu, Ali C. Gurbuz, Evie A. Malaia, Darrin Griffin, Chris Crawford, Sevgi Z. Gurbuz

Figure 1 for ASL Trigger Recognition in Mixed Activity/Signing Sequences for RF Sensor-Based User Interfaces
Figure 2 for ASL Trigger Recognition in Mixed Activity/Signing Sequences for RF Sensor-Based User Interfaces
Figure 3 for ASL Trigger Recognition in Mixed Activity/Signing Sequences for RF Sensor-Based User Interfaces
Figure 4 for ASL Trigger Recognition in Mixed Activity/Signing Sequences for RF Sensor-Based User Interfaces
Viaarxiv icon

MT3: Multi-Task Multitrack Music Transcription

Nov 10, 2021
Josh Gardner, Ian Simon, Ethan Manilow, Curtis Hawthorne, Jesse Engel

Figure 1 for MT3: Multi-Task Multitrack Music Transcription
Figure 2 for MT3: Multi-Task Multitrack Music Transcription
Figure 3 for MT3: Multi-Task Multitrack Music Transcription
Figure 4 for MT3: Multi-Task Multitrack Music Transcription
Viaarxiv icon