{"total":69,"rows":[{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448,"area":null},{"id":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78,"area":null},{"id":"2408.14340","title":"Foundation Models for Music: A Survey","created":"2024-08-26","cited_by_count":37,"area":"diffusion"},{"id":"2305.06594","title":"V2Meow: Meowing to the Visual Beat via Video-to-Music Generation","created":"2023-05-11","cited_by_count":18,"area":null},{"id":"2505.11079","title":"ALLM4ADD: Unlocking the Capabilities of Audio Large Language Models for Audio Deepfake Detection","created":"2025-05-16","cited_by_count":17,"area":null},{"id":"2401.00430","title":"Brain-Conditional Multimodal Synthesis: A Survey and Taxonomy","created":"2023-12-31","cited_by_count":15,"area":null},{"id":"2409.07450","title":"VMAS: Video-to-Music Generation via Semantic Alignment in Web Music Videos","created":"2024-09-11","cited_by_count":15,"area":null},{"id":"2302.06658","title":"In Search for a Generalizable Method for Source Free Domain Adaptation","created":"2023-02-13","cited_by_count":12,"area":null},{"id":"2304.06910","title":"HCAM -- Hierarchical Cross Attention Model for Multi-modal Emotion Recognition","created":"2023-04-14","cited_by_count":11,"area":null},{"id":"2307.11078","title":"Brain2Music: Reconstructing Music from Human Brain Activity","created":"2023-07-20","cited_by_count":10,"area":null},{"id":"2210.00943","title":"Simple Pooling Front-ends For Efficient Audio Classification","created":"2022-10-03","cited_by_count":9,"area":null},{"id":"2408.17352","title":"AASIST3: KAN-Enhanced AASIST Speech Deepfake Detection using SSL Features and Additional Regularization for the ASVspoof 2024 Challenge","created":"2024-08-30","cited_by_count":9,"area":null},{"id":"2109.02774","title":"FastAudio: A Learnable Audio Front-End for Spoof Speech Detection","created":"2021-09-06","cited_by_count":8,"area":null},{"id":"2207.05508","title":"EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use","created":"2022-07-12","cited_by_count":8,"area":null},{"id":"2407.03495","title":"Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations","created":"2024-07-03","cited_by_count":8,"area":null},{"id":"2107.00623","title":"Improving Sound Event Classification by Increasing Shift Invariance in Convolutional Neural Networks","created":"2021-07-01","cited_by_count":5,"area":null},{"id":"2107.03985","title":"Comparing Supervised Models And Learned Speech Representations For Classifying Intelligibility Of Disordered Speech On Selected Phrases","created":"2021-07-08","cited_by_count":5,"area":null},{"id":"2605.21842","title":"Energy-Gated Attention: Spectral Salience as an Inductive Bias for Transformer Attention","created":"2026-05-21","cited_by_count":5,"area":null},{"id":"2109.11010","title":"Alzheimers Dementia Detection using Acoustic & Linguistic features and Pre-Trained BERT","created":"2021-09-22","cited_by_count":4,"area":null},{"id":"2210.01719","title":"Learning Temporal Resolution in Spectrogram for Audio Classification","created":"2022-10-04","cited_by_count":4,"area":null},{"id":"2307.13821","title":"Fitting Auditory Filterbanks with Multiresolution Neural Networks","created":"2023-07-25","cited_by_count":4,"area":null},{"id":"2308.04286","title":"Comparative Analysis of the wav2vec 2.0 Feature Extractor","created":"2023-08-08","cited_by_count":4,"area":null},{"id":"2502.12489","title":"A Comprehensive Survey on Generative AI for Video-to-Music Generation","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2309.05855","title":"Instabilities in Convnets for Raw Audio","created":"2023-09-11","cited_by_count":2,"area":null},{"id":"2311.02369","title":"TACNET: Temporal Audio Source Counting Network","created":"2023-11-04","cited_by_count":2,"area":null},{"id":"2406.07646","title":"Pre-training Feature Guided Diffusion Model for Speech Enhancement","created":"2024-06-11","cited_by_count":2,"area":"diffusion"},{"id":"2408.17358","title":"Hold Me Tight: Stable Encoder-Decoder Design for Speech Enhancement","created":"2024-08-30","cited_by_count":2,"area":null},{"id":"2506.09804","title":"Regularizing Learnable Feature Extraction for Automatic Speech Recognition","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2602.04904","title":"DCER: Dual-Stage Compression and Energy-Based Reconstruction","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2112.08165","title":"Chimpanzee voice prints? Insights from transfer learning experiments from human voices","created":"2021-12-15","cited_by_count":1,"area":null},{"id":"2203.15519","title":"Learning neural audio features without supervision","created":"2022-03-29","cited_by_count":1,"area":null},{"id":"2301.02886","title":"Perceptual-Neural-Physical Sound Matching","created":"2023-01-07","cited_by_count":1,"area":null},{"id":"2412.11943","title":"autrainer: A Modular and Extensible Deep Learning Toolkit for Computer Audition Tasks","created":"2024-12-16","cited_by_count":1,"area":null},{"id":"2505.17091","title":"Large Language Models Implicitly Learn to See and Hear Just By Reading","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2602.23300","title":"A Mixture-of-Experts Model for Multimodal Emotion Recognition in Conversations","created":"2026-02-26","cited_by_count":1,"area":"moe"},{"id":"2607.13393","title":"The Caf\\'e in Amsterdam: When the Incumbent Becomes the Oracle","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2105.11836","title":"A Modulation Front-End for Music Audio Tagging","created":"2021-05-25","cited_by_count":0,"area":null},{"id":"2108.10382","title":"Learning Sparse Analytic Filters for Piano Transcription","created":"2021-08-23","cited_by_count":0,"area":null},{"id":"2109.02773","title":"Complementing Handcrafted Features with Raw Waveform Using a Light-weight Auxiliary Model","created":"2021-09-06","cited_by_count":0,"area":null},{"id":"2206.13365","title":"Interpretable Acoustic Representation Learning on Breathing and Speech Signals for COVID-19 Detection","created":"2022-06-27","cited_by_count":0,"area":null},{"id":"2207.09145","title":"GAFX: A General Audio Feature eXtractor","created":"2022-07-19","cited_by_count":0,"area":null},{"id":"2208.03084","title":"Deep Feature Learning for Medical Acoustics","created":"2022-08-05","cited_by_count":0,"area":null},{"id":"2301.10295","title":"Object Segmentation with Audio Context","created":"2023-01-04","cited_by_count":0,"area":null},{"id":"2303.10446","title":"Content Adaptive Front End For Audio Classification","created":"2023-03-18","cited_by_count":0,"area":null},{"id":"2308.10388","title":"Neural Architectures Learning Fourier Transforms, Signal Processing and Much More....","created":"2023-08-20","cited_by_count":0,"area":null},{"id":"2404.12628","title":"Efficient infusion of self-supervised representations in Automatic Speech Recognition","created":"2024-04-19","cited_by_count":0,"area":null},{"id":"2407.03514","title":"Towards Attention-based Contrastive Learning for Audio Spoof Detection","created":"2024-07-03","cited_by_count":0,"area":null},{"id":"2407.10828","title":"Towards Enhanced Classification of Abnormal Lung sound in Multi-breath: A Light Weight Multi-label and Multi-head Attention Classification Method","created":"2024-07-15","cited_by_count":0,"area":null},{"id":"2409.08997","title":"Biomimetic Frontend for Differentiable Audio Processing","created":"2024-09-13","cited_by_count":0,"area":null},{"id":"2412.00312","title":"Raw Audio Classification with Cosine Convolutional Neural Network (CosCovNN)","created":"2024-11-30","cited_by_count":0,"area":null},{"id":"2505.07709","title":"ISAC: An Invertible and Stable Auditory Filter Bank with Customizable Kernels for ML Integration","created":"2025-05-12","cited_by_count":0,"area":null},{"id":"2507.00755","title":"LearnAFE: Circuit-Algorithm Co-design Framework for Learnable Audio Analog Front-End","created":"2025-07-01","cited_by_count":0,"area":null},{"id":"2507.06152","title":"Aliasing in Convnets: A Frame-Theoretic Perspective","created":"2025-07-08","cited_by_count":0,"area":null},{"id":"2509.10031","title":"Unified Learnable 2D Convolutional Feature Extraction for ASR","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2509.19676","title":"Thinking While Listening: Simple Test Time Scaling For Audio Classification","created":"2025-09-24","cited_by_count":0,"area":"lr"},{"id":"2512.03637","title":"AaSP: Aliasing-aware Self-Supervised Pre-Training for Audio Spectrogram Transformers","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2603.14917","title":"Spectrogram features for audio and speech analysis","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2603.21316","title":"HELIX: Scaling Raw Audio Understanding with Hybrid Mamba-Attention Beyond the Quadratic Limit","created":"2026-03-22","cited_by_count":0,"area":"ssm"},{"id":"2603.25476","title":"How Class Ontology and Data Scale Affect Audio Transfer Learning","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.10503","title":"Cross-Cultural Bias in Mel-Scale Representations: Evidence and Alternatives from Speech and Music","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2606.04210","title":"Representation Matters in Randomized Smoothing for Audio Classification","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.29518","title":"Harvesting AI Computation at the Edge via Generic Approximation","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.08545","title":"Structural Bottlenecks on Frequency Representation in End-to-End Audio Models","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.20086","title":"Cumsum-Composable Phase Transport for Low-Cost Streaming Keyword Spotting","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.23101","title":"PolyChirp: Multi-Species Birdsong Classification Using TinyML on Low-Power Acoustic Sensors","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.25646","title":"LDAC-Net: A Learnable Multi-Lag Differencing Attention-Convolution Network for Drift-Robust Recognition with Low-Cost MOX Gas Sensors","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.29012","title":"Frequency Selective Neural Networks as a Foundation Architecture for Time Series Learning","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.00792","title":"MADS: A Multiview Acoustic Descriptor Set Beyond Standard Spectral Summaries","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.10054","title":"Orukeet: Multilingual ASR with Frozen Gabor Kernels","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}