1

EfficientASR: Speech Recognition Network Compression via Attention Redundancy and Chunk-Level FFN Optimization
In recent years, Transformer networks have shown remarkable performance in speech recognition tasks. However, their deployment poses …
Cite arXiv IEEE
EfficientASR: Speech Recognition Network Compression via Attention Redundancy and Chunk-Level FFN Optimization
Enhancing Anomalous Sound Detection with Multi-Level Memory Bank
Abnormal sound detection (ASD) is crucial for the timely detection of machine faults in industrial scenarios and has emerged as a …
Cite IEEE
Enhancing Anomalous Sound Detection with Multi-Level Memory Bank
Learning Expressive Disentangled Speech Representations with Soft Speech Units and Adversarial Style Augmentation
Voice conversion is the task to transform voice characteristics of source speech while preserving content information. Nowadays, …
Cite arXiv IEEE
Learning Expressive Disentangled Speech Representations with Soft Speech Units and Adversarial Style Augmentation
MAIN-VC: Lightweight Speech Representation Disentanglement for One-Shot Voice Conversion
One-shot voice conversion aims to change the timbre of any source speech to match that of the unseen target speaker with only one …
Cite arXiv DEMO IEEE
MAIN-VC: Lightweight Speech Representation Disentanglement for One-Shot Voice Conversion
PRENet: A Plane-Fit Redundancy Encoding Point Cloud Sequence Network for Real-Time 3D Action Recognition
Recognizing human actions from point cloud sequence has attracted tremendous attention from both academia and industry due to its wide …
Cite arXiv IEEE
PRENet: A Plane-Fit Redundancy Encoding Point Cloud Sequence Network for Real-Time 3D Action Recognition
QLSC: A Query Latent Semantic Calibrator for Robust Extractive Question Answering
Extractive Question Answering (EQA) in Machine Reading Comprehension (MRC) often faces the challenge of dealing with semantically …
Cite arXiv IEEE
QLSC: A Query Latent Semantic Calibrator for Robust Extractive Question Answering
Task-Agnostic Decision Transformer for Multi-Type Agent Control with Federated Split Training
With the rapid advancements in artificial intelligence, the development of knowledgeable and personalized agents has become …
Cite arXiv IEEE
Task-Agnostic Decision Transformer for Multi-Type Agent Control with Federated Split Training
From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning
In the realm of Large Language Models, the balance between instruction data quality and quantity has become a focal point. Recognizing …
Cite Code arXiv
From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning
Medical Speech Symptoms Classification via Disentangled Representation
Intent is defined for understanding spoken language in existing works. Both textual features and acoustic features involved in medical …
Cite arXiv IEEE
Medical Speech Symptoms Classification via Disentangled Representation
Gecko: Resource-Efficient and Accurate Queries in Real-Time Video Streams at the Edge
Surveillance cameras are ubiquitous nowadays and users’ increasing needs for accessing real-world information (e.g., finding abandoned …
PDF Cite
Gecko: Resource-Efficient and Accurate Queries in Real-Time Video Streams at the Edge