Zobrazeno 1 - 10
of 238
pro vyhledávání: '"Chan, Julian"'
Autor:
Knaeble, Brian, Chan, Julian
Publikováno v:
Biometrical Journal, 60(6) 1164-1171 (2018)
This article introduces a new condition based on odds ratios for sensitivity analysis. The analysis involves the average effect of a treatment or exposure on a response or outcome with estimates adjusted for and conditional on a single, unmeasured, d
Externí odkaz:
http://arxiv.org/abs/2310.06808
Autor:
Zhang, Xiaohui, Manohar, Vimal, Zhang, David, Zhang, Frank, Shi, Yangyang, Singhal, Nayan, Chan, Julian, Peng, Fuchun, Saraf, Yatharth, Seltzer, Mike
Hybrid automatic speech recognition (ASR) models are typically sequentially trained with CTC or LF-MMI criteria. However, they have vastly different legacies and are usually implemented in different frameworks. In this paper, by decoupling the concep
Externí odkaz:
http://arxiv.org/abs/2107.04154
Autor:
Le, Duc, Jain, Mahaveer, Keren, Gil, Kim, Suyoun, Shi, Yangyang, Mahadeokar, Jay, Chan, Julian, Shangguan, Yuan, Fuegen, Christian, Kalinli, Ozlem, Saraf, Yatharth, Seltzer, Michael L.
How to leverage dynamic contextual information in end-to-end speech recognition has remained an active research area. Previous solutions to this problem were either designed for specialized use cases that did not generalize well to open-domain scenar
Externí odkaz:
http://arxiv.org/abs/2104.02194
Autor:
Shi, Yangyang, Nagaraja, Varun, Wu, Chunyang, Mahadeokar, Jay, Le, Duc, Prabhavalkar, Rohit, Xiao, Alex, Yeh, Ching-Feng, Chan, Julian, Fuegen, Christian, Kalinli, Ozlem, Seltzer, Michael L.
We propose a dynamic encoder transducer (DET) for on-device speech recognition. One DET model scales to multiple devices with different computation capacities without retraining or finetuning. To trading off accuracy and latency, DET assigns differen
Externí odkaz:
http://arxiv.org/abs/2104.02176
End-to-end models in general, and Recurrent Neural Network Transducer (RNN-T) in particular, have gained significant traction in the automatic speech recognition community in the last few years due to their simplicity, compactness, and excellent perf
Externí odkaz:
http://arxiv.org/abs/2011.07754
Autor:
Zhang, Xiaohui, Zhang, Frank, Liu, Chunxi, Schubert, Kjell, Chan, Julian, Prakash, Pradyot, Liu, Jun, Yeh, Ching-Feng, Peng, Fuchun, Saraf, Yatharth, Zweig, Geoffrey
In this work, to measure the accuracy and efficiency for a latency-controlled streaming automatic speech recognition (ASR) application, we perform comprehensive evaluations on three popular training criteria: LF-MMI, CTC and RNN-T. In transcribing so
Externí odkaz:
http://arxiv.org/abs/2011.04785
Autor:
Yeh, Ching-Feng, Wang, Yongqiang, Shi, Yangyang, Wu, Chunyang, Zhang, Frank, Chan, Julian, Seltzer, Michael L.
Attention-based models have been gaining popularity recently for their strong performance demonstrated in fields such as machine translation and automatic speech recognition. One major challenge of attention-based models is the need of access to the
Externí odkaz:
http://arxiv.org/abs/2011.07120
Autor:
Wang, Yongqiang, Shi, Yangyang, Zhang, Frank, Wu, Chunyang, Chan, Julian, Yeh, Ching-Feng, Xiao, Alex
In this paper, we summarize the application of transformer and its streamable variant, Emformer based acoustic model for large scale speech recognition applications. We compare the transformer based acoustic models with their LSTM counterparts on ind
Externí odkaz:
http://arxiv.org/abs/2010.14665
Autor:
Shi, Yangyang, Wang, Yongqiang, Wu, Chunyang, Yeh, Ching-Feng, Chan, Julian, Zhang, Frank, Le, Duc, Seltzer, Mike
This paper proposes an efficient memory transformer Emformer for low latency streaming speech recognition. In Emformer, the long-range history context is distilled into an augmented memory bank to reduce self-attention's computation complexity. A cac
Externí odkaz:
http://arxiv.org/abs/2010.10759
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.