papers

MeanFlow-TSE: One-Step Generative Target Speaker Extraction with Mean Flow

Speaker Identity is Robustly Encoded in Spatial Patterns of Intracranial EEG for Attention Decoding

Sci-Phi: A Large Language Model Spatial Audio Descriptor

SightSound-R1: Cross-Modal Reasoning Distillation from Vision to Audio Language Models

Layer-wise minimal pair probing reveals contextual grammatical-conceptual hierarchy in speech representations

DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis

Bridging Ears and Eyes: Analyzing Audio and Visual Large Language Models to Humans in Visible Sound Recognition and Reducing Their Sensory Gap via Cross-Modal Distillation

AAD-LLM: Neural Attention-Driven Auditory Scene Understanding

ArrayDPS: Unsupervised Blind Speech Separation with a Diffusion Prior

Exploring finetuned audio-LLM on heart murmur features

Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis

StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion

Just ASR + LLM? A Study on Speech Large Language Models’ Ability to Identify And Understand Speaker in Spoken Dialogue

SSAMBA: Self-Supervised Audio Representation Learning With Mamba State Space Model

StyleTalker: Finetuning Audio Language Model and Style-Based Text-to-Speech Model for Fast Spoken Dialogue Generation

Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation

Listen, Chat, and Remix: Text-Guided Soundscape Remixing for Enhanced Auditory Experience

Exploring self-supervised contrastive learning of spatial sound event representation

Hiftnet: A fast high-quality neural vocoder with harmonic-plus-noise filter and inverse short time fourier transform

Phoneme-level bert for enhanced prosody of text-to-speech with grapheme predictions

DeCoR: Defy Knowledge Forgetting by Predicting Earlier Audio Codes

Learning Representations for New Sound Classes With Continual Self-Supervised Learning

Compute and memory efficient universal sound source separation