How Do Nonlinear Transformers Acquire Generalization-Guaranteed CoT Ability?Hongkang LiMeng Wenget al.2024ICML 2024
Improving RNN Transducer Acoustic Models for English Conversational Speech RecognitionXiaodong CuiGeorge Saonet al.2023INTERSPEECH 2023
Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit QuantizationAndrea FasoliChia-Yu Chenet al.2022INTERSPEECH 2022
Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label SmoothingXiaodong CuiGeorge Saonet al.2022INTERSPEECH 2022
M2 ASR: Multilingual Multi-task Automatic Speech Recognition via Multi-objective OptimizationA SaifLisha Chenet al.2024INTERSPEECH 2024
How Can Personalized Context Help? Exploring Joint Retrieval of Passage and Personalized ContextHui WanHongkang Liet al.2024ICASSP 2024
Joint Unsupervised and Supervised Training for Automatic Speech Recognition via Bilevel OptimizationA F M SaifXiaodong Cuiet al.2024ICASSP 2024
Diagonal State Space Augmented Transformers for Speech RecognitionGeorge SaonAnkit Guptaet al.2023ICASSP 2023