Search Results for author:
Found 11 papers, 2 papers with code
Partial Federated Learning
Federated Learning (FL) is a popular algorithm to train machine learning models on user data constrained to edge devices (for example, mobile phones) due to privacy concerns.
Coordinated Replay Sample Selection for Continual Federated Learning
Continual Federated Learning (CFL) combines Federated Learning (FL), the decentralized learning of a central model on a number of client devices that may not communicate their data, and Continual Learning (CL), the learning of a model from a continual stream of data without keeping the entire history.
End-to-end spoken language understanding using joint CTC loss and self-supervised, pretrained acoustic encoders
It is challenging to extract semantic meanings directly from audio signals in spoken language understanding (SLU), due to the lack of textual information.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
How to Minimize the Weighted Sum AoI in Multi-Source Status Update Systems: OMA or NOMA?
In this paper, the minimization of the weighted sum average age of information (AoI) in a multi-source status update communication system is studied.
On the data requirements of probing
As large and powerful neural language models are developed, researchers have been increasingly interested in developing diagnostic tools to probe them.
Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation
Large pretrained language models (LMs) like BERT have improved performance in many disparate natural language processing (NLP) tasks.
Speaker attribution with voice profiles by graph-based semi-supervised learning
Speaker attribution is required in many real-world applications, such as meeting transcription, where speaker identity is assigned to each utterance according to speaker voice profiles.
Encoding Syntactic Knowledge in Transformer Encoder for Intent Detection and Slot Filling
We propose a novel Transformer encoder-based architecture with syntactical knowledge encoded for intent detection and slot filling.
Speaker diarization with session-level speaker embedding refinement using graph neural networks
Deep speaker embedding models have been commonly used as a building block for speaker diarization systems; however, the speaker embedding model is usually trained according to a global loss defined on the training data, which could be sub-optimal for distinguishing speakers locally in a specific meeting session.
Training without training data: Improving the generalizability of automated medical abbreviation disambiguation
Abbreviation disambiguation is important for automated clinical note processing due to the frequent use of abbreviations in clinical settings.
Centroid-based deep metric learning for speaker recognition
Speaker embedding models that utilize neural networks to map utterances to a space where distances reflect similarity between speakers have driven recent progress in the speaker recognition task.
