Audio Representation Learning

Follow this topic Ask about this topic

Momentum

20 papers in the last four weeks, up 233% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 141

All topics

How Far Do Foundation Models Transfer to Infant Signals? A Cross-Dataset Transfer Audit with a Unified Need Ontology
Aug 10, 2026Wu HangyuAudio Representation Learning Domain-Adaptive Pretraining
Shenzhen Coddie Technology Co., Ltd.
Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning
Aug 6, 2026Zezhong Jin, Xiaoyu Wang, Zhe Li +4Audio Representation Learning Residual Learning
Dept. of EEE, The Hong Kong Polytechnic University · Baidu Inc. · Speech, Language, and Cognition Laboratory, The University of Hong Kong, Hong Kong SAR
MeloCodec: Harnessing Melodic Priors for High-Fidelity Singing Voice Representation
Aug 4, 2026Yizhong Geng, Wenxin Fu, Kecan Mao +7Audio Representation Learning Neural Audio Codecs
Beijing University of Posts and Telecommunications, Beijing, China · Li Auto, Beijing, China
Discriminative Axis, Not Data Volume: What a Contrastive Corpus Teaches an Audio Embedding
Aug 3, 2026Abdul Basit TonmoyContrastive Learning Audio Representation Learning
Eximius Labs · Wabash College
Stable Autoregressive Speech Generation with Low-Frame-Rate High-Dimensional Continuous Tokens
Jul 31, 2026Yi Luo, Rongzhi Gu, Jixun YaoFlow Matching Audio Representation Learning
ByteDance Seed · Work done during an internship at ByteDance Seed.
Do Music Foundation Models Embed Pitch in Helical Structure?
Jul 31, 2026Hayato Yagi, Shinnosuke Takamichi, Rin Sato +2Audio Representation Learning Neural Representation Geometry
Keio University, Japan · The University of Tokyo, Japan · Waseda University, Japan
Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens
Jul 28, 2026Daigo Takizawa, Tomohiko Nakamura, Samuele Cornell +3Audio Representation Learning Neural Audio Codecs
National Institute of Advanced Industrial Science and Technology (AIST), Japan · Carnegie Mellon University, USA
Mind the Microphone Gap: Benchmarking Array Upsampling Strategies for Latent Acoustic Mapping
Jul 27, 2026Philipp Schmidt, Huw Cheston, Juan Azcarreta +3Audio Representation Learning Self-Supervised Learning
Queen Mary University of London · Meta Reality Labs Research
Phylogenetic signal in marine mammal and bird vocalizations captured by audio foundation models: the limited benefit of domain-specific pretraining
Jul 24, 2026Víctor Rincón YepesAudio Representation Learning Bioacoustics
Independent Researcher
Reflector: Arrangement-Aware Harmonic Retrieval for Sample-Based Composition
Jul 24, 2026Austin RockmanAudio Representation Learning Music Information Retrieval
Independent Researcher
Music-JEPA: Learning a World Model of Sound from Action
Jul 24, 2026Ziyu Wang, Kun Fang, Yann LeCunAudio Representation Learning World Model Learning
Courant Institute, New York University · Schulich School of Music, McGill University · Centre for Interdisciplinary Research in Music Media and Technology (CIRMMT) +2
HARP: Harmonic-Aware Residual Partitioning for Neural Audio Codecs
Jul 18, 2026Qiaoyu Yang, Lixing He, Binyue Deng +1Audio Representation Learning Neural Audio Codecs
Georgia Institute of Technology, Atlanta, United States · The Chinese University of Hong Kong, Hong Kong, China · Tencent Music Entertainment, Shenzhen, China
StemFX: Learning Mixing Style Representations via Autoregressive FX Chain Prediction on Source-Separated Stems
Jul 17, 2026Yuan-Chiao Cheng, Jui-Te Wu, Brian Chen +3Audio Representation Learning
Independent Researcher · National Taiwan University, Taiwan · AI-CoRE, National Taiwan University, Taiwan
Can Tokens Compete? Token Representations against Supervised CNN Backbones for BirdCLEF+ 2026
Jul 16, 2026Anthony Miyaguchi, Murilo Gustineli, Adrian CheungAudio Representation Learning Neural Audio Codecs
Georgia Institute of Technology, 225 North Ave NW, Atlanta, GA 30332 · 1Georgia Institute of Technology, 225 North Ave NW, Atlanta, GA 30332
ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Models
Jul 10, 2026Sang-Hoon Lee, Ha-Yeong ChoiAudio Representation Learning Latent Diffusion Models
Department of Artificial Intelligence, Ajou University, Suwon, Korea · KT Corp., Seoul, Korea
Structural Bottlenecks on Frequency Representation in End-to-End Audio Models
Jul 9, 2026Nicole Cosme-CliffordAudio Representation Learning Neural Audio Codecs
Yale University New Haven, CT
Escaping the Procrustean Bed: Groupwise Orthogonal Connectors for Audio-Language Models
Jul 7, 2026Ho-Lam Chung, Ke-Han Lu, Yi-Cheng Lin +3Audio Representation Learning Representation Learning
Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan · ASUS AICS, Taipei, Taiwan
A Self-Supervised Approach for Minimal-Annotation Hydroacoustic Data Exploration
Jul 7, 2026Pierre-Yves Raumer, Axel Marmoret, Dorian Cazau +6Audio Representation Learning Self-Supervised Learning
Laboratoire de G´eologie, Ecole Normale Sup´erieure/CNRS UMR 8538, PSL Research University, Paris 75005, France · Universit´e de Brest, CNRS, Ifremer, UMR6538 Geo-Ocean, 29280 Plouzan´e, France · Lab-STICC – UMR 6285 CNRS, ENSTA IP Paris, Brest, France +5
Streaming Neural Speech Codecs through Time-Invariant Representations
Jul 6, 2026Kélian Estève, Salima Mhdaffar, Mickael Rouvier +2Audio Representation Learning Neural Audio Codecs
LIA, Avignon Universit´e, France · LS2N, Nantes Universit´e, France
CARD: Cross-component Audio Representation Distillation for Encoder-Free Audio Captioning
Jul 6, 2026Ganesh Pavan Kartikeya Bharadwaj Kolluri, Yuchen Zhang, Michael Kampouridis +1Audio Representation Learning Audio-Language Models
School of Computer Science and Electronic Engineering, University of Essex · Institute for Analytics and Data Science, University of Essex
Doppelganger: Sound Effects and Their Synthetic Twins
Jul 5, 2026Elliott AshAudio Representation Learning Audio Deepfake Detection
ETH Zürich
Probing Low-Level Acoustic Attribute Encoding in CLAP Audio Embeddings
Jul 4, 2026Héctor Martel, Joe Hennessy-Priest, Taemin ChoRepresentation Geometry Audio Representation Learning
BandLab Technologies, Singapore
Taste-aware music retrieval from audio embeddings
Jul 3, 2026Matteo Spanio, Antonio RodàAudio Representation Learning Cross-Modal Retrieval
University of Padua, Padua, Italy
Quantifying the Uncertainty of Blindly Estimated Room Embeddings Using a Dispersion-Calibrated Score
Jul 1, 2026Yang Xiang, Philipp Götz, Emanuël A. P. Habets +3Audio Representation Learning Representation Learning
Centre for Vision Speech and Signal Processing, University of Surrey, United Kingdom · International Audio Laboratories Erlangen∗, Erlangen, Germany · Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany
Evaluating Pretrained Music Embeddings for Cross-Performance Jazz Standard Recognition
Jul 1, 2026Çağrı EserAudio Representation Learning Music Information Retrieval
Department of Computer Engineering, Middle East Technical University, Ankara, Turkey.
BEST-RQ-2: Contextualize-Then-Predict, a Two-Step Approach for Self-Supervised Audio Representations
Jun 29, 2026Ludovic K. Tuncay, Etienne Labbé, Thomas PellegriniAudio Representation Learning Self-Supervised Pre-Training
IRIT-SAMoVA · IRIT, Université de Toulouse, CNRS, Toulouse INP, Toulouse, France
ALM2Vec: Learning Audio Embeddings for Universal Audio Retrieval with Large Audio-Language Models
Jun 27, 2026Fengjie Lu, Chenang Jiang, Jiarui Hai +2Audio Representation Learning Audio-Language Models
Zhejiang University · Johns Hopkins University
From General-Purpose Audio Tagging to Spatially Grounded Sound Event Localization and Detection
Jun 26, 2026Stefano Giacomelli, Stefano Damiano, Claudia Rinaldi +2Audio Representation Learning Direction-of-Arrival Estimation
DISIM Department, University of L’Aquila, Italy · ESAT Department, KU Leuven, Belgium · CNIT, Research Unit of L’Aquila, Italy +1
wav2tok 2.0: Scalable Audio Tokenization Maintaining Explicit Pairwise Token Alignment for Efficient Audio Retrieval
Jun 25, 2026Adhiraj Banerjee, Vipul AroraAudio Representation Learning Speech Processing
Department of Electrical Engineering, Indian Institute of Technology Kanpur, India · Department of Electrical Engineering, KU Leuven, Belgium
WQ-Fusion: Dynamic Gated Attention for Cross-Domain Audio Representation
Jun 25, 2026Mingda Lin, Lei Ding, Xinyue Zhou +6Audio Representation Learning Gated Attention
School of Electronic Information, Wuhan University, Wuhan, Hubei, China · Tencent AI Lab Seattle, Seattle, USA · CIAIC, Northwestern Polytechnical University, Xi’an, Shaanxi, China +1

Aug 10, 2026, cs.CLJ/K move · Enter open · S save

How Far Do Foundation Models Transfer to Infant Signals? A Cross-Dataset Transfer Audit with a Unified Need Ontology

Wu Hangyu

Shenzhen Coddie Technology Co., Ltd.

Audio Representation Learning Domain-Adaptive Pretraining Cross-Domain Transfer Learning Audio Classification

Open paper AskPDF arXiv

Public infant cry corpora are small, label-incompatible, and almost always evaluated one corpus at a time. We ask what this practice hides and what fixes it. Across four cry corpora screened by a multi-level leakage audit (byte-level and embedding-level deduplication plus a within-corpus train-test near-duplicate audit), we probe four frozen encoders and a handcrafted baseline under a unified five-class need ontology and shared task formulations. The audit exposes what single-corpus evaluation conceals: within-domain macro-F1 swings by 0.57-0.80 for the same encoder, cross-corpus transfer is negative on average (negative-transfer ratio 0.19-0.35, significant in 18 of 30 directed cells, BH-FDR), and 349 content-identical clip groups carry conflicting metadata labels across corpus distributions. The same audit, however, reveals a consistent way forward. Transfer into the noisiest corpus is consistently positive in effect size at matched training size and after near-duplicate removal, offering a practical recipe for small, noisy corpora. Frozen probes saturate at modest label budgets, while stabilized fine-tuning wins with full labels; domain-adaptive pretraining significantly beats stabilized fine-tuning at 5-10-shot (the 1-shot advantage is not robust to optimization-seed variance) but shows no significant advantage at 50-shot or beyond. In the tested binary, shared-label settings, ontology-mapped joint training wins in all four encoder-by-target combinations, whereas naively merging unmapped labels costs up to 37 F1 points. We release the ontology, mapping code, and audit pipeline, turning incompatible cry corpora into a usable joint-training resource.

Momentum

Related topics

Latest papers 141