ICASSP 2023

VF-TACO2: TOWARDS FAST AND LIGHTWEIGHT SYNTHESIS FOR AUTOREGRESSIVE MODELS WITH VARIATION AUTOENCODER AND FEATURE DISTILLATION

EVALUATING PARAMETER-EFFICIENT TRANSFER LEARNING APPROACHES ON SURE BENCHMARK FOR SPEECH UNDERSTANDING

Multi-User Data Detection in Massive MIMO with 1-Bit ADCs

Full-band General Audio Synthesis with Score-based Diffusion

Phase-Aware Spoof Speech Detection Based on Res2Net with Phase Network

SUBBAND DEPENDENCY MODELING FOR SOUND EVENT DETECTION

RADIO SENSING WITH LARGE INTELLIGENT SURFACE FOR 6G

AV-SepFormer: Cross-attention SepFormer for Audio-Visual Target Speaker Extraction

ZO-DARTS: DIFFERENTIABLE ARCHITECTURE SEARCH WITH ZEROTH-ORDER APPROXIMATION

Gaussian Prior Reinforcement Learning for Nested Named Entity Recognition

A Deep Temporal Factor Analysis Method for Large Scale Financial Portfolio Selection

Role of Lexical Boundary Information in Chunk-Level Segmentation for Speech Emotion Recognition