Search Results for author: Jinglun Cai

Found 5 papers, 1 papers with code

Zero-Shot End-to-End Spoken Language Understanding via Cross-Modal Selective Self-Training

1 code implementation22 May 2023 Jianfeng He, Julian Salazar, Kaisheng Yao, Haoqi Li, Jinglun Cai

End-to-end (E2E) spoken language understanding (SLU) is constrained by the cost of collecting speech-semantics pairs, especially when label domains change.

Natural Language Understanding Spoken Language Understanding

Masked Audio Text Encoders are Effective Multi-Modal Rescorers

no code implementations11 May 2023 Jinglun Cai, Monica Sunkara, Xilai Li, Anshu Bhatia, Xiao Pan, Sravan Bodapati

Masked Language Models (MLMs) have proven to be effective for second-pass rescoring in Automatic Speech Recognition (ASR) systems.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Balancing Multi-Domain Corpora Learning for Open-Domain Response Generation

no code implementations Findings (NAACL) 2022 Yujie Xing, Jinglun Cai, Nils Barlaug, Peng Liu, Jon Atle Gulla

Furthermore, we propose Domain-specific Frequency (DF), a novel word-level importance weight that measures the relative importance of a word for a specific corpus compared to other corpora.

Response Generation

Cannot find the paper you are looking for? You can Submit a new open access paper.