Extending RNN-T-based speech recognition systems with emotion and language classificationZvi KonsHagai Aronowitzet al.2022INTERSPEECH 2022
Global RNN Transducer Models For Multi-dialect Speech RecognitionTakashi FukudaSamuel Thomaset al.2022INTERSPEECH 2022
VQ-T: RNN Transducers using Vector-Quantized Prediction Network StatesJiatong ShiGeorge Saonet al.2022INTERSPEECH 2022
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
4-bit quantization of LSTM-based speech recognition modelsAndrea FasoliChia-Yu Chenet al.2021INTERSPEECH 2021
Integrating dialog history into end-to-end spoken language understanding systemsJatin GanhotraSamuel Thomaset al.2021INTERSPEECH 2021
On the limit of English conversational speech recognitionZoltan TuskeGeorge Saonet al.2021INTERSPEECH 2021
Improving customization of neural transducers by mitigating acoustic mismatch of synthesized audioGakuto KurataGeorge Saonet al.2021INTERSPEECH 2021
Reducing exposure bias in training recurrent neural network transducersXiaodong CuiBrian Kingsburyet al.2021INTERSPEECH 2021