Spoken semantic parsing (SSP) involves generating machine-comprehensible...
End-to-end (E2E) spoken language understanding (SLU) systems that genera...
Autoregressive (AR) encoder-decoder neural networks have proved successf...
In Federated Learning (FL), accessing private client data incurs
communi...
Recent studies find existing self-supervised speech encoders contain
pri...
We propose a novel deliberation-based approach to end-to-end (E2E) spoke...
Task-oriented semantic parsing models have achieved strong results in re...
Data efficiency, despite being an attractive characteristic, is often
ch...
When tuning the architecture and hyperparameters of large machine learni...
An effective recipe for building seq2seq, non-autoregressive, task-orien...
Task-oriented semantic parsing models typically have high resource
requi...
Semantic parsing using sequence-to-sequence models allows parsing of dee...
We propose pre-finetuning, an additional large-scale learning stage betw...
The structured representation for semantic parsing in task-oriented assi...
Although widely adopted, existing approaches for fine-tuning pre-trained...