{"total":68,"rows":[{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2402.07729","title":"AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension","created":"2024-02-12","cited_by_count":220,"area":null},{"id":"2309.14405","title":"Joint Audio and Speech Understanding","created":"2023-09-25","cited_by_count":100,"area":null},{"id":"2405.00233","title":"SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound","created":"2024-04-30","cited_by_count":45,"area":null},{"id":"2505.15957","title":"Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey","created":"2025-05-21","cited_by_count":39,"area":null},{"id":"2306.10548","title":"MARBLE: Music Audio Representation Benchmark for Universal Evaluation","created":"2023-06-18","cited_by_count":38,"area":null},{"id":"2504.12880","title":"Can Masked Autoencoders Also Listen to Birds?","created":"2025-04-17","cited_by_count":26,"area":null},{"id":"2508.04665","title":"Perch 2.0: The Bittern Lesson for Bioacoustics","created":"2025-08-06","cited_by_count":26,"area":null},{"id":"2406.16148","title":"Towards Open Respiratory Acoustic Foundation Models: Pretraining and Benchmarking","created":"2024-06-23","cited_by_count":23,"area":null},{"id":"2309.10787","title":"AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models","created":"2023-09-19","cited_by_count":19,"area":null},{"id":"2312.07439","title":"BIRB: A Generalization Benchmark for Information Retrieval in Bioacoustics","created":"2023-12-12","cited_by_count":19,"area":null},{"id":"2506.05140","title":"AudioLens: A Closer Look at Auditory Attribute Perception of Large Audio-Language Models","created":"2025-06-05","cited_by_count":18,"area":null},{"id":"2405.00934","title":"Benchmarking Representations for Speech, Music, and Acoustic Events","created":"2024-05-02","cited_by_count":15,"area":null},{"id":"2306.00561","title":"Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners","created":"2023-06-01","cited_by_count":11,"area":null},{"id":"2505.03054","title":"BLAB: Brutally Long Audio Bench","created":"2025-05-05","cited_by_count":11,"area":null},{"id":"2206.12038","title":"BYOL-S: Learning Self-supervised Speech Representations by Bootstrapping","created":"2022-06-24","cited_by_count":10,"area":null},{"id":"2309.07391","title":"EnCodecMAE: Leveraging neural codecs for universal audio representation learning","created":"2023-09-14","cited_by_count":9,"area":null},{"id":"2408.02514","title":"Stem-JEPA: A Joint-Embedding Predictive Architecture for Musical Stem Compatibility Estimation","created":"2024-08-05","cited_by_count":8,"area":null},{"id":"2604.19300","title":"HalluAudio: A Comprehensive Benchmark for Hallucination Detection in Large Audio-Language Models","created":"2026-04-21","cited_by_count":8,"area":null},{"id":"2505.06224","title":"Towards a Unified Representation Evaluation Framework Beyond Downstream Tasks","created":"2025-05-09","cited_by_count":7,"area":null},{"id":"2506.18843","title":"USAD: Universal Speech and Audio Representation via Distillation","created":"2025-06-23","cited_by_count":7,"area":null},{"id":"2509.24901","title":"Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2209.12900","title":"The Efficacy of Self-Supervised Speech Models for Audio Representations","created":"2022-09-26","cited_by_count":6,"area":null},{"id":"2308.04258","title":"Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Sets","created":"2023-08-08","cited_by_count":6,"area":null},{"id":"2209.14345","title":"Audio Barlow Twins: Self-Supervised Audio Representation Learning","created":"2022-09-28","cited_by_count":5,"area":null},{"id":"2307.05161","title":"On the Effectiveness of Speech Self-supervised Learning for Music","created":"2023-07-11","cited_by_count":5,"area":null},{"id":"2508.11845","title":"AVEX: What Matters for Animal Vocalization Encoding","created":"2025-08-15","cited_by_count":5,"area":null},{"id":"2211.13956","title":"Learning General Audio Representations with Large-Scale Training of Patchout Audio Transformers","created":"2022-11-25","cited_by_count":4,"area":null},{"id":"2405.06128","title":"Enhanced Multimodal Content Moderation of Children's Videos using Audiovisual Fusion","created":"2024-05-09","cited_by_count":4,"area":null},{"id":"2502.12031","title":"Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2505.06660","title":"TS-SUPERB: A Target Speech Processing Benchmark for Speech Self-Supervised Learning Models","created":"2025-05-10","cited_by_count":4,"area":null},{"id":"2511.16757","title":"Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation","created":"2025-11-20","cited_by_count":4,"area":null},{"id":"2304.11472","title":"A Comparative Study of Pre-trained Speech and Audio Embeddings for Speech Emotion Recognition","created":"2023-04-22","cited_by_count":3,"area":null},{"id":"2410.00511","title":"Pre-training with Synthetic Patterns for Audio","created":"2024-10-01","cited_by_count":3,"area":null},{"id":"2506.17055","title":"Universal Music Representations? Evaluating Foundation Models on World Music Corpora","created":"2025-06-20","cited_by_count":3,"area":null},{"id":"2211.06646","title":"Efficient Speech Quality Assessment using Self-supervised Framewise Embeddings","created":"2022-11-12","cited_by_count":2,"area":null},{"id":"2406.06341","title":"Predicting Heart Activity from Speech using Data-driven and Knowledge-based features","created":"2024-06-10","cited_by_count":2,"area":null},{"id":"2406.15897","title":"Fusing Audio and Metadata Embeddings Improves Language-based Audio Retrieval","created":"2024-06-22","cited_by_count":2,"area":null},{"id":"2409.08673","title":"Acoustic identification of individual animals with hierarchical contrastive learning","created":"2024-09-13","cited_by_count":2,"area":null},{"id":"2409.09511","title":"Explaining Deep Learning Embeddings for Speech Emotion Recognition by Predicting Interpretable Acoustic Features","created":"2024-09-14","cited_by_count":2,"area":null},{"id":"2507.16696","title":"FISHER: A Foundation Model for Multi-Modal Industrial Signal Comprehensive Representation","created":"2025-07-22","cited_by_count":2,"area":null},{"id":"2601.08358","title":"Linear probing enables Ship-Radiated Noise recognition with pretrained audio embeddings","created":"2026-01-13","cited_by_count":2,"area":null},{"id":"2312.14005","title":"On the choice of the optimal temporal support for audio classification with Pre-trained embeddings","created":"2023-12-21","cited_by_count":1,"area":null},{"id":"2406.05923","title":"Contrastive Learning from Synthetic Audio Doppelg\\\"angers","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2409.09378","title":"Prevailing Research Areas for Music AI in the Era of Foundation Models","created":"2024-09-14","cited_by_count":1,"area":null},{"id":"2412.17306","title":"Multiple Consistency-guided Test-Time Adaptation for Contrastive Audio-Language Models with Unlabeled Audio","created":"2024-12-23","cited_by_count":1,"area":null},{"id":"2502.06664","title":"Evaluation of Deep Audio Representations for Hearables","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2602.21772","title":"UniWhisper: Efficient Continual Multi-task Training for Robust Universal Audio Representation","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2606.06444","title":"USAD 2.0: Scaling Representation Distillation for Universal Audio Understanding","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2607.03296","title":"Taste-aware music retrieval from audio embeddings","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2607.05365","title":"SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2303.03591","title":"Approach to Learning Generalized Audio Representation Through Batch Embedding Covariance Regularization and Constant-Q Transforms","created":"2023-03-07","cited_by_count":0,"area":null},{"id":"2304.02160","title":"Pac-HuBERT: Self-Supervised Music Source Separation via Primitive Auditory Clustering and Hidden-Unit BERT","created":"2023-04-04","cited_by_count":0,"area":null},{"id":"2306.05915","title":"Speaker Embeddings as Individuality Proxy for Voice Stress Detection","created":"2023-06-09","cited_by_count":0,"area":null},{"id":"2306.11764","title":"On Frequency-Wise Normalizations for Better Recording Device Generalization in Audio Spectrogram Transformers","created":"2023-06-20","cited_by_count":0,"area":null},{"id":"2309.11895","title":"Audio Contrastive-based Fine-tuning: Decoupling Representation Learning and Classification","created":"2023-09-21","cited_by_count":0,"area":null},{"id":"2411.19806","title":"Zero-shot Musical Stem Retrieval with Joint-Embedding Predictive Architectures","created":"2024-11-29","cited_by_count":0,"area":null},{"id":"2505.11889","title":"Revisiting SSL for sound event detection: complementary fusion and adaptive post-processing","created":"2025-05-17","cited_by_count":0,"area":null},{"id":"2505.21025","title":"Text-Queried Audio Source Separation via Hierarchical Modeling","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2506.01275","title":"Contra4: Evaluating Contrastive Cross-Modal Reasoning in Audio, Video, Image, and 3D","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2510.10948","title":"Unify Variables in Neural Scaling Laws for General Audio Representations via Embedding Effective Rank","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2511.07205","title":"Twenty-Five Years of MIR Research: Achievements, Practices, Evaluations, and Future Challenges","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2511.16849","title":"Better audio representations are more brain-like: linking model-brain alignment with performance in downstream auditory tasks","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2602.16305","title":"BAT: Better Audio Transformer Guided by Convex Gated Probing","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2606.14662","title":"Beyond task performance: Decoding bioacoustic embeddings with speech features","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2608.14819","title":"What Makes a Good Layer? Assessing the Layer-Wise Intrinsic Properties of Music Foundation Models","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.15221","title":"MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-Training","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.27195","title":"Quieter Than the Room: Representation Drift and Task Robustness in Speech Encoders","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}