Speech Recognition using Biologically-Inspired Neural NetworksThomas BohnstinglAyush Garget al.2022ICASSP 2022
Integrating Text Inputs For Training and Adapting RNN Transducer ASR ModelsSamuel ThomasBrian Kingsburyet al.2022ICASSP 2022
Integrating dialog history into end-to-end spoken language understanding systemsJatin GanhotraSamuel Thomaset al.2021INTERSPEECH 2021
Improving customization of neural transducers by mitigating acoustic mismatch of synthesized audioGakuto KurataGeorge Saonet al.2021INTERSPEECH 2021
4-bit quantization of LSTM-based speech recognition modelsAndrea FasoliChia-Yu Chenet al.2021INTERSPEECH 2021
On the limit of English conversational speech recognitionZoltan TuskeGeorge Saonet al.2021INTERSPEECH 2021
Reducing exposure bias in training recurrent neural network transducersXiaodong CuiBrian Kingsburyet al.2021INTERSPEECH 2021
Advancing RNN transducer technology for speech recognitionGeorge SaonZoltan Tuskeet al.2021ICASSP 2021
RNN transducer models for spoken language understandingSamuel ThomasHong-Kwang J. Kuoet al.2021ICASSP 2021
Asynchronous Decentralized Distributed Training of Acoustic ModelsXiaodong CuiWei Zhanget al.2021IEEE/ACM TASLP