research
∙
05/22/2023
Zero-Shot End-to-End Spoken Language Understanding via Cross-Modal Selective Self-Training
End-to-end (E2E) spoken language understanding (SLU) is constrained by t...
share
research
∙
05/11/2023
Masked Audio Text Encoders are Effective Multi-Modal Rescorers
Masked Language Models (MLMs) have proven to be effective for second-pas...
research
∙
05/05/2023
Mask The Bias: Improving Domain-Adaptive Generalization of CTC-based ASR with Internal Language Model Estimation
End-to-end ASR models trained on large amount of data tend to be implici...
research
∙
05/05/2022