Alert button
Picture for Masayuki Suzuki

Masayuki Suzuki

Alert button

Multiple Representation Transfer from Large Language Models to End-to-End ASR Systems

Sep 07, 2023
Takuma Udagawa, Masayuki Suzuki, Gakuto Kurata, Masayasu Muraoka, George Saon

Viaarxiv icon

Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systems

Apr 01, 2022
Takuma Udagawa, Masayuki Suzuki, Gakuto Kurata, Nobuyasu Itoh, George Saon

Figure 1 for Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systems
Figure 2 for Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systems
Figure 3 for Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systems
Figure 4 for Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systems
Viaarxiv icon

Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing

Mar 29, 2022
Xiaodong Cui, George Saon, Tohru Nagano, Masayuki Suzuki, Takashi Fukuda, Brian Kingsbury, Gakuto Kurata

Figure 1 for Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing
Figure 2 for Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing
Figure 3 for Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing
Figure 4 for Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing
Viaarxiv icon

English Broadcast News Speech Recognition by Humans and Machines

Apr 30, 2019
Samuel Thomas, Masayuki Suzuki, Yinghui Huang, Gakuto Kurata, Zoltan Tuske, George Saon, Brian Kingsbury, Michael Picheny, Tom Dibert, Alice Kaiser-Schatzlein, Bern Samko

Figure 1 for English Broadcast News Speech Recognition by Humans and Machines
Figure 2 for English Broadcast News Speech Recognition by Humans and Machines
Figure 3 for English Broadcast News Speech Recognition by Humans and Machines
Figure 4 for English Broadcast News Speech Recognition by Humans and Machines
Viaarxiv icon