Spoken document retrieval and written text mining

M3ST: MIX AT THREE LEVELS FOR SPEECH TRANSLATION

FULLY UNSUPERVISED TOPIC CLUSTERING OF UNLABELLED SPOKEN AUDIO USING SELF-SUPERVISED REPRESENTATION LEARNING AND TOPIC MODEL

Efficient Uncertainty Estimation with Gaussian Process for Reliable Dialog Response Retrieval

MHLAT: Multi-hop Label-wise Attention Model for Automatic ICD Coding

Leveraging Large Text Corpora for End-to-End Speech Summarization

Knowledge-aware Few Shot Learning for Event Detection from Short Texts

Coarse-to-Fine Knowledge Selection for Document Grounded Dialogs

Matching-based Term Semantics Pre-training for Spoken Patient Query Understanding

SPTEAE: A SOFT PROMPT TRANSFER MODEL FOR ZERO-SHOT CROSS-LINGUAL EVENT ARGUMENT EXTRACTION

A mutual implicit sentiment analysis model with bundle-aware contrastive learning

Speech summarization of long spoken document: Improving memory efficiency of speech/text encoders

SPATIAL-DOMAIN OBJECT DETECTION UNDER MIMO-FMCW AUTOMOTIVE RADAR INTERFERENCE