Alert button
Picture for Zoltán Tüske

Zoltán Tüske

Alert button

4-bit Quantization of LSTM-based Speech Recognition Models

Aug 27, 2021
Andrea Fasoli, Chia-Yu Chen, Mauricio Serrano, Xiao Sun, Naigang Wang, Swagath Venkataramani, George Saon, Xiaodong Cui, Brian Kingsbury, Wei Zhang, Zoltán Tüske, Kailash Gopalakrishnan

Figure 1 for 4-bit Quantization of LSTM-based Speech Recognition Models
Figure 2 for 4-bit Quantization of LSTM-based Speech Recognition Models
Figure 3 for 4-bit Quantization of LSTM-based Speech Recognition Models
Figure 4 for 4-bit Quantization of LSTM-based Speech Recognition Models
Viaarxiv icon

Integrating Dialog History into End-to-End Spoken Language Understanding Systems

Aug 18, 2021
Jatin Ganhotra, Samuel Thomas, Hong-Kwang J. Kuo, Sachindra Joshi, George Saon, Zoltán Tüske, Brian Kingsbury

Figure 1 for Integrating Dialog History into End-to-End Spoken Language Understanding Systems
Figure 2 for Integrating Dialog History into End-to-End Spoken Language Understanding Systems
Figure 3 for Integrating Dialog History into End-to-End Spoken Language Understanding Systems
Figure 4 for Integrating Dialog History into End-to-End Spoken Language Understanding Systems
Viaarxiv icon

On the limit of English conversational speech recognition

May 03, 2021
Zoltán Tüske, George Saon, Brian Kingsbury

Figure 1 for On the limit of English conversational speech recognition
Figure 2 for On the limit of English conversational speech recognition
Figure 3 for On the limit of English conversational speech recognition
Viaarxiv icon

RNN Transducer Models For Spoken Language Understanding

Apr 08, 2021
Samuel Thomas, Hong-Kwang J. Kuo, George Saon, Zoltán Tüske, Brian Kingsbury, Gakuto Kurata, Zvi Kons, Ron Hoory

Figure 1 for RNN Transducer Models For Spoken Language Understanding
Figure 2 for RNN Transducer Models For Spoken Language Understanding
Figure 3 for RNN Transducer Models For Spoken Language Understanding
Figure 4 for RNN Transducer Models For Spoken Language Understanding
Viaarxiv icon

End-to-End Spoken Language Understanding Without Full Transcripts

Sep 30, 2020
Hong-Kwang J. Kuo, Zoltán Tüske, Samuel Thomas, Yinghui Huang, Kartik Audhkhasi, Brian Kingsbury, Gakuto Kurata, Zvi Kons, Ron Hoory, Luis Lastras

Figure 1 for End-to-End Spoken Language Understanding Without Full Transcripts
Figure 2 for End-to-End Spoken Language Understanding Without Full Transcripts
Figure 3 for End-to-End Spoken Language Understanding Without Full Transcripts
Figure 4 for End-to-End Spoken Language Understanding Without Full Transcripts
Viaarxiv icon

Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard-300

Jan 20, 2020
Zoltán Tüske, George Saon, Kartik Audhkhasi, Brian Kingsbury

Figure 1 for Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard-300
Figure 2 for Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard-300
Figure 3 for Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard-300
Figure 4 for Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard-300
Viaarxiv icon

Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural Networks

Oct 16, 2018
Xiaodong Cui, Wei Zhang, Zoltán Tüske, Michael Picheny

Figure 1 for Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural Networks
Figure 2 for Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural Networks
Figure 3 for Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural Networks
Viaarxiv icon