Topics / Sound / Oct 19 - 25, 2026
Weekly issue
Top 20 Sound Papers: Oct 19 - 25, 2026
- 1SLM-SS: Token-Based Speech Separation with Speech Language Models
Existing speech separation systems are mostly optimized with signal-level objectives, and often yield outputs that are acceptable in waveform metrics but suboptimal for intelligibility-sensitive downstream tasks. To address this gap, we propose SLM-SS, a token-based generative speech separation framework that models multi-talker mixtures with speech language models.
- 2Known Music, Unknown Response: Leakage-Audited Dynamic Arousal Forecasting With Scheduled Future Music
The study provides a leakage-controlled reference for known-future music forecasting without treating predictive substitutions as causal interventions.
- 3Long Listening Thoughts: Eliciting Open Auditory Reasoning with Deliberative Perception and Cognitive Refinement
We introduce Long Listening Thoughts (LLT), a framework for constructing post-training datasets that improves audio reasoning by pairing deliberate perceptual grounding with explicit cognitive behaviors.
- 4MuLaCover: Flexible Cover Song Generation Via Symbolic Tonal Control
To this end, we present MuLaCover, a cover generation model that conditions a pretrained text-to-song foundation model on an editable symbolic lead sheet.
- 5Uncovering Audio-Text Alignment in Large Audio-Language Models Through Cross-Modal Concept Neurons
We hypothesize that there is a shared subspace where the audio and text representations are aligned.
Get papers like these the day they come out, not a week later.
Follow this category- 6Jarvis: Coordination Deserves A Brain of Its Own in Agentic Interactive Models
We introduce Jarvis, a coordination harness where models judge and code enforces.
- 7ConvexLLM: Scaling Convex-Hull Speech Interfaces to General-Purpose Audio Intelligence
We present ConvexLLM, a general-purpose speech and audio language model whose C-Gate interface represents audio as continuous convex combinations of frozen text embeddings.
- 8Flash RNN-T: Memory-Efficient Joint Network and Transducer Loss Computation
We present Flash RNN-T, a joint and loss implementation combining specialized kernels with optional tiled recomputation over the full alignment space and vocabulary.
- 9VoxDub: A Bilingual Lip-Synchronized Audio-Visual Dataset for Automatic Video Dubbing
We introduce VoxDub, a bilingual lip-synchronized audio-visual dataset containing 766K clips and approximately 1.58K hours of in-the-wild Chinese and English recordings, covering varied speakers, scenes, speaking styles, and linguistic content.
- 10Improved Automatic Speech-based Cognitive Assessment Using Neuropsychologically Calibrated Diagnostic Labels
We analysed 138 hours of conversational speech from 720 participants, recalibrating unreliable diagnostic labels using attention, executive function, and memory performance via external clinical thresholds, Gaussian, and normative z-score calibration.
- 11Point2Acoustic: Efficient Room Acoustic Parameter Estimation from 3D Geometry and Material Properties
We present Point2Acoustic, a learning-based framework for direct estimation of six-band reverberation time ($RT_{60}$) and reverberant-to-direct ratio (RDR) from 3D scene geometry and acoustic material properties.
- 12D-Composer: Language Modeling for Simultaneous Drum Transcription and Sound Event Decomposition
However, leading AbS approaches struggle to generalize to a broad range of drum timbres (e.g., electronic drum kits), rely on high-quality paired audio-transcription training data, and do not model intra-class timbral variation within a single arrangement (e.g., multiple kick sounds). To overcome these limitations, we propose D-Composer, an autoregressive language modeling framework that decomposes drum recordings into labeled sound events and their onset times.
- 13EmoFI-TTS: Face-Conditioned Expressive Voice Synthesis with Intensity Modulation
We propose EmoFI-TTS, a face-conditioned framework that derives emotion category and intensity from a single facial image while extracting speaker characteristics from reference audio.
- 14MarineSet: Large-Scale Underwater Acoustic Data Curation and Evaluation
However, large-scale data alone does not guarantee effective representation learning, because model performance is strongly influenced by the distribution of the training data. To facilitate such training data, this study introduces a scalable curation pipeline that curates 3,000 hours from 41 years of raw NOAA hydrophone recordings, producing MarineSet, a large-scale and diverse dataset designed for underwater acoustic learning.
- 15PhonoBridge: Error-Aware Phoneme-Mediated EMG-to-Text Reconstruction
We introduce PhonoBridge, a two-stage framework comprising a channel-aware EMG-to-phoneme frontend and a large language model (LLM) backend for text reconstruction.
- 16Query-Conditioned Liquid Temporal Grounding for Long-Form Audio
We propose a query-conditioned liquid temporal grounding framework that injects query semantics through FiLM before a closed-form continuous-time (CfC) network models long-range temporal dependencies.
- 17Agentic Music Post-Production
We introduce MixAgent, an agentic pipeline for music post-production that follows the workflow of audio engineers to build interpretable and editable mixing plans guided by a reference song.
- 18UniAVC: Unified Audio-Video Creation Via Progressive Training and Asymmetric Scheduling
We present UniAVC, which addresses both obstacles.
- 19RubatoCodec: Budgeted Adaptive Speech Tokenization with Streaming Decoding
We present RubatoCodec, a variable-frame-rate speech codec built on X-Codec-2 with an exact utterance-level event budget and streaming decoding.
- 20StyleStream 2.0: Fast and Controllable Streaming Voice Style Conversion
StyleStream 1.0 introduced the first streamable zero-shot VSC system with state-of-the-art conversion quality, but remained limited in two ways: approximately 1s end-to-end latency on consumer hardware, and the lack of a text-based interface for designing or editing target voices. We present StyleStream 2.0, a fast and controllable streaming VSC framework that addresses these limitations.