Topics / Sound / Oct 5 - 11, 2026
Weekly issue
Top 20 Sound Papers: Oct 5 - 11, 2026
- 1EchoChat: Structured Cognitive Reasoning in Empathetic Spoken Dialogue
In this work, we propose EchoChat, a unified framework that reformulates empathetic spoken dialogue as a structured cognitive reasoning process integrating perception, mental-state reasoning, and response generation.
- 2SheetSage2: Coherent Lead-Sheet Transcription with Synthetic Supervision
We present SheetSage2, a unified music transcription framework that combines synthetic data, task-specific structured decoding, and autoregressive distillation.
- 3Listen-to-Reason: Listen with Experts, Retrieve Over A Graph, Reason with LLMs
This coupling means that a new domain or a stronger LLM requires retraining, and their answers cannot be traced to what the model heard: a chain-of-thought is a post-hoc account. We propose Listen-to-Reason (L2R), an interpretable-by-design pipeline that passes audio to the LLM through an explicit, human-readable tree: small heads on frozen expert encoders map each chunk of a clip to semantically meaningful nodes on the tree (for speech, music and environmental sound), and a frozen text-only LLM answers from these nodes and an ASR transcript without hearing the clip.
- 4Personalized Automatic Speech Recognition for A Dysarthric and Tracheostomic Speaker Using Artificial Conversations
We propose a multi-stage training pipeline based on Whisper Base: fine-tuning on standard Czech speech, acoustically simulated tracheostomic speech, and the speaker's data.
- 5WorldSonus: Bringing Sound to Worlds
Bringing sound to world models poses three core challenges: real-time generation to keep pace with interactive video streams, interactive control to respond to mid-stream sound instructions, and spatially aligned stereo to reflect scene geometry and camera motion. To address these demands, we introduce WorldSonus, an interactive video-to-audio framework designed for real-time spatial sound synthesis in world models.
Get papers like these the day they come out, not a week later.
Follow this category- 6CrossEdit: Cross-Modal Training Enables Rich Audio-Visual Editing
We present CrossEdit, a unified omni-modal editing model for images, audio, and video that performs AV movie scene edits zero-shot through cross-modal transfer.
- 7Logbook: Extremely Long-form Audio Event Understanding
Audio benchmarks are built around short, pre-segmented clips, limiting model design to brief inputs or fixed vocabularies. To close this gap, we introduce Logbook, a benchmark for hour-scale audio understanding, with recordings ranging from ten minutes to six days.
- 8Can LLM Agents Automate Reinforcement Learning for Text-to-Speech?
Although reinforcement learning (RL) post-training repairs the localized segmental errors of zero-shot text-to-speech (TTS), arriving at a working recipe still relies on tedious manual tuning, and whether LLM agents can take over this research pipeline is unclear. We investigate this question with AgenticTTS-Forge, a collaborative workflow that structures human guidance and agentic execution around a shared workspace, applied to CosyVoice2-0.5B. To measure what the agent automates, we audit its trajectory stage by stage against the published recipe.
- 9AuraSE: Low-Hallucination Generative Speech Enhancement Via Multimodal Flow Matching and Inference Policy Optimization
We present AuraSE, a flow-matching framework that addresses hallucination through complementary modality and inference designs.
- 10DuplexAgent-RSI: Recursive Harness Improvement for Full-Duplex Voice Agent Collaboration
Existing harnesses often rely on coupled heuristics, making them difficult to improve systematically from evidence. We present DuplexAgent, a full-duplex collaboration system whose harness expresses this workflow as six editable modules, and Duplex-Harness-RSI, a closed loop that revises them from interaction traces.
- 11AraYoungVoices: A Diverse L1/L2 Corpus of Arabic Child and Adolescent Speech
We introduce AraYoungVoices, a 151.72-hour Arabic read-speech corpus from 286 speakers aged 7--18, comprising AraKids (7--12) and AraTeens (13--18).
- 12Smorph: Playable Sound Morphing with Diffusion Models
We present smorph, a training-free guidance framework that preserves how a sound behaves over time while transforming what the sound is, allowing users to morph, for instance from brass to strings at a fixed pitch.
- 13
- 14Beyond Perturbation Magnitude: Direction-Dependent Responses in Multimodal Geometric Representations
Using frozen cohorts from MSR-VTT (N=878) and DiDeMo (N=980), we apply controlled video blur and audio noise and analyze the response in the relational geometry on which the score is defined.
- 15DriftTTS: Few-Step Text-to-Speech Without Distillation Via Distribution-Matching Drift
Few-step neural text-to-speech models often rely on short- ened diffusion or flow-matching schedules, or on distillation from pretrained multi-step teachers. To avoid these depen- dencies, we present DriftTTS, a few-step mel-spectrogram generator trained without a generative teacher, distillation, or adversarial discrimination.
- 16Rubric-Based Optimization for Text-to-Music Generation
We study structured, rubric-based rewards from pretrained audio-language models (ALMs) as training signals for both autoregressive and diffusion-based music generators.
- 17ParaGeo: Decomposing Paralinguistic Variation Into A Shared Latent Geometry
We introduce ParaGeo, a matched-content decomposition of paralinguistic variation in a frozen speech language model.
- 18ARIA: Audio-Driven Melody-Tone Relation Modeling for Cantonese Lyric Authoring
However, in real songwriting scenarios, melodies are often expressed as raw singing audio or hummed recordings, where pitch is implicit, noisy, and unstructured, making these methods difficult to apply directly. To address this limitation, we propose ARIA, a two-stage audio-driven melody-tone relation modeling framework for Cantonese lyric authoring that generates Cantonese lyrics from singing recordings with provided character-level timestamps.
- 19Hiding Tool Latency in On-Device Cascaded Voice Agent Through Speculative Execution
We present speculative tool execution for on-device cascaded voice agents, which predicts tool requests from partial ASR hypotheses and initiates tool execution while speech is still being received, thereby reducing end-to-end response latency.
- 20HiPLEX: Hierarchical Policy Factorization for Full Duplex Speech Language Models
We introduce HiPLEX, an RL framework that factorizes a pretrained full-duplex text policy into a control policy that decides when to emit content and a conditional content policy that decides what to emit.