 Fine-tuning Is a Surprisingly Effective Domain Adaptation Baseline in Handwriting RecognitionIEEE International Conference on Document Analysis and Recognition (ICDAR), 2023 |
 Speaker Adaptation for End-To-End Speech Recognition Systems in Noisy
EnvironmentsAutomatic Speech Recognition & Understanding (ASRU), 2022 |
 Modular Hybrid Autoregressive TransducerSpoken Language Technology Workshop (SLT), 2022 |
 Speaker Identity Preservation in Dysarthric Speech Reconstruction by
Adversarial Speaker AdaptationIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022 |
 Minimum Word Error Rate Training with Language Model Fusion for
End-to-End Speech RecognitionInterspeech (Interspeech), 2021 |
 Internal Language Model Training for Domain-Adaptive End-to-End Speech
RecognitionIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021 |
 L-Vector: Neural Label Embedding for Domain AdaptationIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020 |
 Domain Adaptation via Teacher-Student Learning for End-to-End Speech
RecognitionAutomatic Speech Recognition & Understanding (ASRU), 2019 |
 Speaker Adaptation for Attention-Based End-to-End Speech RecognitionInterspeech (Interspeech), 2019 |
 Adversarial Speaker VerificationIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019 |
 Attentive Adversarial Learning for Domain-Invariant TrainingIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019 |
 Conditional Teacher-Student LearningIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019 |
