Man-Machine Speech Communication

Ultra-Low Complexity Residue Echo and Noise Suppression Based on Recurrent Neural Network.- Semi-End-to-End Nested Named Entity Recognition from Speech.- A Lightweight Music Source Separation Model with Graph Convolution Network.- Joint time-domain and frequency-domain progressive learning for single-channel speech enhancement and recognition.- A Study on Domain Adaptation for Audio-visual Speech Enhancement.- APNet2: High-quality and High-efficiency Neural Vocoder with Direct Prediction of Amplitude and Phase Spectra.- Within- and Between-Class Sample Interpolation Based Supervised Metric Learning for Speaker Verification.- Joint speech and noise estimation using SNR-adaptive target learning for deep-learning-based speech enhancement.- Data Augmentation By Finite Element Analysis for Enhanced Machine Anomalous Sound Detection.- A Fast Sampling Method in Diffusion-based Dance Generation Models.- End-to-end Streaming Customizable KeywordSpotting based on text-adaptive neural search.- The Production of Successive Addition Boundary Tone in Mandarin Preschoolers.- Emotional Support Dialog System Through Recursive Interactions Among Large Language Models.- Task-Adaptive Generative Adversarial Network based Speech Dereverberation for Robust Speech Recognition.- Real-time Automotive Engine Sound Simulation with Deep Neural Network.- A Framework Combining Separate and Joint Training for Neural Vocoder-Based Monaural Speech Enhancement.- Accent-VITS: accent transfer for end-to-end TTS.- Multi-branch Network with Cross-Domain Feature Fusion for Anomalous Sound Detection.- A Packet Loss Concealment Method Based on the Demucs Network Structure.- Improving Speech Perceptual Quality and Intelligibility through Sub-band Temporal Envelope Characteristics.- Adaptive Deep Graph Convolutional Network For Dialogical Speech Emotion Recognition.- Iterative Noisy-target Approach: Speech Enhancement without Clean Speech.- Joint Training or Not: An Exploration of Pre-trained Speech Models in Audio-Visual Speaker Diarization.- Zero-shot Singing Voice Conversion Method Based on Timbre Space Modeling and Excitation Signal Control.- A Comparative Study of Pre-trained Audio and Speech Models for Heart Sound Detection.- CAM-GUI: A Conversational Assistant on Mobile GUI.- A Pilot Study on the Prosodic Factors Influencing Voice Attractiveness of AI Speech.- The DKU-MSXF Diarization System for the VoxCeleb Speaker Recognition Challenge 2023.- Chinese EFL Learners’ Auditory and Visual Perception of English Statement and Question Intonation: The Effect of Stress.- An Improved System for Partially Fake Audio Detection Using Pre-trained Model.- Leveraging Synthetic Speech for CIF-based Customized Keyword Spotting.