{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/audio-classification/papers/3","list_of":"/task/audio-classification","task":"Audio Classification","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":3,"pages_in_order":4,"rows_per_page":100,"rows":[201,300],"of":361,"counts":{"archive_papers_tagged":361,"with_a_code_link":183,"where_syntology_ran_a_sample":46,"not_listed_spam_title":0,"listed":361,"listed_where_code_ran":46,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":41,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":41,"listed_every_run_a_failure_of_syntologys_instrument":5,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/audio-classification","prev":"/task/audio-classification/papers/2","next":"/task/audio-classification/papers/4","papers":[{"url":null,"slug":"audio-classification-of-low-feature","title":"Audio Classification of Low Feature Spectrograms Utilizing Convolutional Neural Networks","date":"2024-10-28","arxiv_id":"2410.21561","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-speech-and-more-investigating-the","title":"Beyond Speech and More: Investigating the Emergent Ability of Speech Foundation Models for Classifying Physiological Time-Series Signals","date":"2024-10-16","arxiv_id":"2410.12645","repositories_listed":0,"syntology":null},{"url":null,"slug":"spectral-and-rhythm-features-for-audio","title":"Spectral and Rhythm Features for Audio Classification with Deep Convolutional Neural Networks","date":"2024-10-09","arxiv_id":"2410.06927","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multimodal-framework-for-deepfake-detection","title":"A Multimodal Framework for Deepfake Detection","date":"2024-10-04","arxiv_id":"2410.03487","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-sound-description-exploring-prompt-1","title":"A sound description: Exploring prompt templates and class descriptions to enhance zero-shot audio classification","date":"2024-09-19","arxiv_id":"2409.13676","repositories_listed":0,"syntology":null},{"url":null,"slug":"deft-mamba-universal-multichannel-sound","title":"DeFT-Mamba: Universal Multichannel Sound Separation and Polyphonic Audio Classification","date":"2024-09-19","arxiv_id":"2409.12413","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-framework-for-synthetic-audio-conversations","title":"A Framework for Synthetic Audio Conversations Generation using Large Language Models","date":"2024-09-02","arxiv_id":"2409.00946","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-label-zero-shot-audio-classification","title":"Multi-label Zero-Shot Audio Classification with Temporal Attention","date":"2024-08-31","arxiv_id":"2409.00408","repositories_listed":0,"syntology":null},{"url":null,"slug":"modalitymirror-improving-audio-classification","title":"ModalityMirror: Improving Audio Classification in Modality Heterogeneity Federated Learning with Multimodal Distillation","date":"2024-08-28","arxiv_id":"2408.15803","repositories_listed":0,"syntology":null},{"url":null,"slug":"eavit-external-attention-vision-transformer","title":"EAViT: External Attention Vision Transformer for Audio Classification","date":"2024-08-23","arxiv_id":"2408.13201","repositories_listed":0,"syntology":null},{"url":null,"slug":"dilated-convolution-with-learnable-spacings-2","title":"Dilated Convolution with Learnable Spacings","date":"2024-08-10","arxiv_id":"2408.06383","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrasting-deep-learning-models-for-direct","title":"Contrasting Deep Learning Models for Direct Respiratory Insufficiency Detection Versus Blood Oxygen Saturation Estimation","date":"2024-07-30","arxiv_id":"2407.20989","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-robust-few-shot-class-incremental","title":"Towards Robust Few-shot Class Incremental Learning in Audio Classification using Contrastive Representation","date":"2024-07-27","arxiv_id":"2407.19265","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-continual-learning-for-robust","title":"Advancing Continual Learning for Robust Deepfake Audio Classification","date":"2024-07-14","arxiv_id":"2407.10108","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-learning-from-synthetic-audio","title":"Contrastive Learning from Synthetic Audio Doppelgängers","date":"2024-06-09","arxiv_id":"2406.05923","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-feature-fusion-network-via","title":"Attention Feature Fusion Network via Knowledge Propagation for Automated Respiratory Sound Classification","date":"2024-05-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"afen-respiratory-disease-classification-using","title":"AFEN: Respiratory Disease Classification using Ensemble Learning","date":"2024-05-08","arxiv_id":"2405.05467","repositories_listed":0,"syntology":null},{"url":null,"slug":"audioprotopnet-an-interpretable-deep-learning","title":"AudioProtoPNet: An interpretable deep learning model for bird sound classification","date":"2024-04-16","arxiv_id":"2404.10420","repositories_listed":0,"syntology":null},{"url":"/paper/mixer-is-more-than-just-a-model","slug":"mixer-is-more-than-just-a-model","title":"Mixer is more than just a model","date":"2024-02-28","arxiv_id":"2402.18007","repositories_listed":0,"syntology":null},{"url":null,"slug":"tuning-in-analysis-of-audio-classifier","title":"Tuning In: Analysis of Audio Classifier Performance in Clinical Settings with Limited Data","date":"2024-02-07","arxiv_id":"2402.10100","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-coarse-to-fine-efficient-training-for","title":"From Coarse to Fine: Efficient Training for Audio Spectrogram Transformers","date":"2024-01-16","arxiv_id":"2401.08415","repositories_listed":0,"syntology":null},{"url":null,"slug":"class-incremental-learning-for-multi-label","title":"Class-Incremental Learning for Multi-Label Audio Classification","date":"2024-01-09","arxiv_id":"2401.04447","repositories_listed":0,"syntology":null},{"url":"/paper/omnivec2-a-novel-transformer-based-network","slug":"omnivec2-a-novel-transformer-based-network","title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-choice-of-the-optimal-temporal-support","title":"On the choice of the optimal temporal support for audio classification with Pre-trained embeddings","date":"2023-12-21","arxiv_id":"2312.14005","repositories_listed":0,"syntology":null},{"url":null,"slug":"pruning-random-resistive-memory-for","title":"Pruning random resistive memory for optimizing analogue AI","date":"2023-11-13","arxiv_id":"2311.07164","repositories_listed":0,"syntology":null},{"url":"/paper/mirasol3b-a-multimodal-autoregressive-model","slug":"mirasol3b-a-multimodal-autoregressive-model","title":"Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities","date":"2023-11-09","arxiv_id":"2311.05698","repositories_listed":0,"syntology":null},{"url":"/paper/omnivec-learning-robust-representations-with","slug":"omnivec-learning-robust-representations-with","title":"OmniVec: Learning robust representations with cross modal sharing","date":"2023-11-07","arxiv_id":"2311.05709","repositories_listed":0,"syntology":null},{"url":null,"slug":"explore-the-effect-of-data-selection-on","title":"Explore the Effect of Data Selection on Poison Efficiency in Backdoor Attacks","date":"2023-10-15","arxiv_id":"2310.09744","repositories_listed":0,"syntology":null},{"url":null,"slug":"compa-addressing-the-gap-in-compositional","title":"CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models","date":"2023-10-12","arxiv_id":"2310.08753","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-models-as-masked-audio-video","title":"Diffusion Models as Masked Audio-Video Learners","date":"2023-10-05","arxiv_id":"2310.03937","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-contrastive-based-fine-tuning","title":"Audio Contrastive based Fine-tuning","date":"2023-09-21","arxiv_id":"2309.11895","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-speech-recognition-for-african","title":"Improving Speech Recognition for African American English With Audio Classification","date":"2023-09-16","arxiv_id":"2309.09996","repositories_listed":0,"syntology":null},{"url":null,"slug":"diverse-neural-audio-embeddings-bringing","title":"Diverse Audio Embeddings-- Bringing Features Back Outperforms CLAP !","date":"2023-09-15","arxiv_id":"2309.08751","repositories_listed":0,"syntology":null},{"url":null,"slug":"cpsp-learning-speech-concepts-from-phoneme","title":"Learning Speech Representation From Contrastive Token-Acoustic Pretraining","date":"2023-09-01","arxiv_id":"2309.00424","repositories_listed":0,"syntology":null},{"url":"/paper/real-time-detection-of-ai-generated-speech","slug":"real-time-detection-of-ai-generated-speech","title":"Real-time Detection of AI-Generated Speech for DeepFake Voice Conversion","date":"2023-08-24","arxiv_id":"2308.12734","repositories_listed":0,"syntology":null},{"url":null,"slug":"lcanets-robust-audio-classification-using","title":"LCANets++: Robust Audio Classification using Multi-layer Neural Networks with Lateral Competition","date":"2023-08-23","arxiv_id":"2308.12882","repositories_listed":0,"syntology":null},{"url":null,"slug":"bavs-bootstrapping-audio-visual-segmentation","title":"BAVS: Bootstrapping Audio-Visual Segmentation by Integrating Foundation Knowledge","date":"2023-08-20","arxiv_id":"2308.10175","repositories_listed":0,"syntology":null},{"url":null,"slug":"audioformer-audio-transformer-learns-audio","title":"AudioFormer: Audio Transformer learns audio feature representations from discrete acoustic codes","date":"2023-08-14","arxiv_id":"2308.07221","repositories_listed":0,"syntology":null},{"url":null,"slug":"detection-of-children-abuse-by-voice-and","title":"Detection of Children Abuse by Voice and Audio Classification by Short-Time Fourier Transform Machine Learning implemented on Nvidia Edge GPU device","date":"2023-07-27","arxiv_id":"2307.15101","repositories_listed":0,"syntology":null},{"url":null,"slug":"flexiast-flexibility-is-what-ast-needs","title":"FlexiAST: Flexibility is What AST Needs","date":"2023-07-18","arxiv_id":"2307.09286","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-classification-using-ml-methods","title":"Audio classification using ML methods","date":"2023-05-30","arxiv_id":"2305.19304","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-language-audio-models-as-few-shot","title":"Adapting Language-Audio Models as Few-Shot Audio Learners","date":"2023-05-28","arxiv_id":"2305.17719","repositories_listed":0,"syntology":null},{"url":null,"slug":"lean-light-and-efficient-audio-classification","title":"LEAN: Light and Efficient Audio Classification Network","date":"2023-05-22","arxiv_id":"2305.12712","repositories_listed":0,"syntology":null},{"url":null,"slug":"tackling-interpretability-in-audio","title":"Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorization","date":"2023-05-11","arxiv_id":"2305.07132","repositories_listed":0,"syntology":null},{"url":null,"slug":"compressing-audio-cnns-with-graph-centrality","title":"Compressing audio CNNs with graph centrality based filter pruning","date":"2023-05-05","arxiv_id":"2305.03391","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-sequence-labeling-for-audio","title":"Transformer-based Sequence Labeling for Audio Classification based on MFCCs","date":"2023-04-30","arxiv_id":"2305.00417","repositories_listed":0,"syntology":null},{"url":"/paper/multiscale-audio-spectrogram-transformer-for","slug":"multiscale-audio-spectrogram-transformer-for","title":"Multiscale Audio Spectrogram Transformer for Efficient Audio Classification","date":"2023-03-19","arxiv_id":"2303.10757","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-content-adaptive-learnable-time-frequency","title":"Content Adaptive Front End For Audio Classification","date":"2023-03-18","arxiv_id":"2303.10446","repositories_listed":0,"syntology":null},{"url":null,"slug":"halluaudio-hallucinating-frequency-as","title":"HalluAudio: Hallucinating Frequency as Concepts for Few-Shot Audio Classification","date":"2023-02-27","arxiv_id":"2302.14204","repositories_listed":0,"syntology":null},{"url":"/paper/adaptive-axonal-delays-in-feedforward-spiking","slug":"adaptive-axonal-delays-in-feedforward-spiking","title":"Adaptive Axonal Delays in feedforward spiking neural networks for accurate spoken word recognition","date":"2023-02-16","arxiv_id":"2302.08607","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-visual-contrastive-learning-with","title":"Audio-Visual Contrastive Learning with Temporal Self-Supervision","date":"2023-02-15","arxiv_id":"2302.07702","repositories_listed":0,"syntology":null},{"url":null,"slug":"semanticac-semantics-assisted-framework-for","title":"SemanticAC: Semantics-Assisted Framework for Audio Classification","date":"2023-02-12","arxiv_id":"2302.05940","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-transformers-for-primates","title":"Visual Transformers for Primates Classification and Covid Detection","date":"2022-12-20","arxiv_id":"2212.10093","repositories_listed":0,"syntology":null},{"url":null,"slug":"pex-memory-efficient-microcontroller-deep","title":"Pex: Memory-efficient Microcontroller Deep Learning through Partial Execution","date":"2022-11-30","arxiv_id":"2211.17246","repositories_listed":0,"syntology":null},{"url":null,"slug":"spectnet-end-to-end-audio-signal","title":"SpectNet : End-to-End Audio Signal Classification Using Learnable Spectrograms","date":"2022-11-17","arxiv_id":"2211.09352","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-sound-audio-classification-with-the","title":"\"Seeing Sound\": Audio Classification with the Wigner-Wille Distribution and Convolutional Neural Networks","date":"2022-11-06","arxiv_id":"2211.03202","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-re-calibration-of-channel-wise","title":"Adaptive re-calibration of channel-wise features for Adversarial Audio Classification","date":"2022-10-21","arxiv_id":"2210.11722","repositories_listed":0,"syntology":null},{"url":"/paper/avt-audio-video-transformer-for-multimodal","slug":"avt-audio-video-transformer-for-multimodal","title":"AVT: Audio-Video Transformer for Multimodal Action Recognition","date":"2022-09-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/multiscale-multimodal-transformer-for","slug":"multiscale-multimodal-transformer-for","title":"Multiscale Multimodal Transformer for Multimodal Action Recognition","date":"2022-09-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/investigating-current-based-and-gating","slug":"investigating-current-based-and-gating","title":"Investigating current-based and gating approaches for accurate and energy-efficient spiking recurrent neural networks","date":"2022-09-15","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-analytics-based-human-trafficking","title":"Audio Analytics-based Human Trafficking Detection Framework for Autonomous Vehicles","date":"2022-09-09","arxiv_id":"2209.04071","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-environmental-perception-of","title":"Improving the Environmental Perception of Autonomous Vehicles using Deep Learning-based Audio Classification","date":"2022-09-09","arxiv_id":"2209.04075","repositories_listed":0,"syntology":null},{"url":null,"slug":"hardware-accelerator-and-neural-network-co","title":"Hardware Accelerator and Neural Network Co-Optimization for Ultra-Low-Power Audio Processing Devices","date":"2022-09-08","arxiv_id":"2209.03807","repositories_listed":0,"syntology":null},{"url":"/paper/western-mediterranean-wetlands-bird-species","slug":"western-mediterranean-wetlands-bird-species","title":"Western Mediterranean wetlands bird species classification: evaluating small-footprint deep learning approaches on a new annotated dataset","date":"2022-07-12","arxiv_id":"2207.05393","repositories_listed":0,"syntology":null},{"url":"/paper/0-1-deep-neural-networks-via-block-coordinate","slug":"0-1-deep-neural-networks-via-block-coordinate","title":"0/1 Deep Neural Networks via Block Coordinate Descent","date":"2022-06-19","arxiv_id":"2206.09379","repositories_listed":0,"syntology":null},{"url":null,"slug":"binary-early-exit-network-for-adaptive","title":"Binary Early-Exit Network for Adaptive Inference on Low-Resource Devices","date":"2022-06-17","arxiv_id":"2206.09029","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-multi-feature-selection-and","title":"Investigating Multi-Feature Selection and Ensembling for Audio Classification","date":"2022-06-15","arxiv_id":"2206.07511","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-informed-embedding-space","title":"Feature-informed Embedding Space Regularization For Audio Classification","date":"2022-06-10","arxiv_id":"2206.04850","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-audio-classification-using-image","title":"Zero-Shot Audio Classification using Image Embeddings","date":"2022-06-10","arxiv_id":"2206.04984","repositories_listed":0,"syntology":null},{"url":null,"slug":"augmentation-induced-consistency","title":"Augmentation-induced Consistency Regularization for Classification","date":"2022-05-25","arxiv_id":"2205.12461","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-tuberculosis-and-covid-19-cough","title":"Automatic Tuberculosis and COVID-19 cough classification using deep learning","date":"2022-05-11","arxiv_id":"2205.05480","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-negative-sampling-for-audio-visual","title":"On Negative Sampling for Audio-Visual Contrastive Learning from Movies","date":"2022-04-29","arxiv_id":"2205.00073","repositories_listed":0,"syntology":null},{"url":"/paper/a-domain-transfer-based-data-augmentation","slug":"a-domain-transfer-based-data-augmentation","title":"A DOMAIN TRANSFER BASED DATA AUGMENTATION METHOD FOR AUTOMATED RESPIRATORY CLASSIFICATION","date":"2022-04-27","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-speaker-identification-using","title":"Few-Shot Speaker Identification Using Depthwise Separable Convolutional Network with Channel Attention","date":"2022-04-24","arxiv_id":"2204.11180","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-neural-audio-features-without","title":"Learning neural audio features without supervision","date":"2022-03-29","arxiv_id":"2203.15519","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-architecture-search-for-energy","title":"Neural Architecture Search for Energy Efficient Always-on Audio Models","date":"2022-02-09","arxiv_id":"2202.05397","repositories_listed":0,"syntology":null},{"url":null,"slug":"connecting-the-dots-between-audio-and-text-1","title":"Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/arsc-net-adventitious-respiratory-sound","slug":"arsc-net-adventitious-respiratory-sound","title":"ARSC-Net: Adventitious Respiratory Sound Classification Network Using Parallel Paths with Channel-Spatial Attention","date":"2022-01-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"augmented-contrastive-self-supervised","title":"Augmented Contrastive Self-Supervised Learning for Audio Invariant Representations","date":"2021-12-21","arxiv_id":"2112.10950","repositories_listed":0,"syntology":null},{"url":null,"slug":"polyvit-co-training-vision-transformers-on-1","title":"PolyViT: Co-training Vision Transformers on Images, Videos and Audio","date":"2021-11-25","arxiv_id":"2111.12993","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-neuromorphic-signal-processing-with","title":"Efficient Neuromorphic Signal Processing with Loihi 2","date":"2021-11-05","arxiv_id":"2111.03746","repositories_listed":0,"syntology":null},{"url":"/paper/temporal-knowledge-distillation-for-on-device","slug":"temporal-knowledge-distillation-for-on-device","title":"Temporal Knowledge Distillation for On-device Audio Classification","date":"2021-10-27","arxiv_id":"2110.14131","repositories_listed":0,"syntology":null},{"url":null,"slug":"defensive-tensorization","title":"Defensive Tensorization","date":"2021-10-26","arxiv_id":"2110.13859","repositories_listed":0,"syntology":null},{"url":"/paper/conformer-based-self-supervised-learning-for","slug":"conformer-based-self-supervised-learning-for","title":"Conformer-Based Self-Supervised Learning for Non-Speech Audio Tasks","date":"2021-10-14","arxiv_id":"2110.07313","repositories_listed":0,"syntology":null},{"url":null,"slug":"spliceout-a-simple-and-efficient-audio","title":"SpliceOut: A Simple and Efficient Audio Augmentation Method","date":"2021-09-30","arxiv_id":"2110.00046","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-interval-retrieval-using-convolutional","title":"Audio Interval Retrieval using Convolutional Neural Networks","date":"2021-09-21","arxiv_id":"2109.09906","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-investigation-into-audio","title":"An empirical investigation into audio pipeline approaches for classifying bird species","date":"2021-08-10","arxiv_id":"2108.04449","repositories_listed":0,"syntology":null},{"url":"/paper/lung-sound-classification-using-co-tuning-and","slug":"lung-sound-classification-using-co-tuning-and","title":"Lung Sound Classification Using Co-tuning and Stochastic Normalization","date":"2021-08-04","arxiv_id":"2108.01991","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-head-relevance-weighting-framework","title":"A Multi-Head Relevance Weighting Framework For Learning Raw Waveform Audio Representations","date":"2021-07-30","arxiv_id":"2107.14793","repositories_listed":0,"syntology":null},{"url":"/paper/temporal-wise-attention-spiking-neural","slug":"temporal-wise-attention-spiking-neural","title":"Temporal-wise Attention Spiking Neural Networks for Event Streams Classification","date":"2021-07-25","arxiv_id":"2107.11711","repositories_listed":0,"syntology":null},{"url":null,"slug":"over-parameterization-and-generalization-in","title":"Over-Parameterization and Generalization in Audio Classification","date":"2021-07-19","arxiv_id":"2107.08933","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-fine-tuning-of-autoencoders-for-fuzzy-rule","title":"On fine-tuning of Autoencoders for Fuzzy rule classifiers","date":"2021-06-21","arxiv_id":"2106.11182","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-federated-learning-with-new-classes","title":"Zero-Shot Federated Learning with New Classes for Audio Classification","date":"2021-06-18","arxiv_id":"2106.10019","repositories_listed":0,"syntology":null},{"url":null,"slug":"belabbert-a-dutch-roberta-based-language","title":"belabBERT: a Dutch RoBERTa-based language model applied to psychiatric classification","date":"2021-06-02","arxiv_id":"2106.01091","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-layer-vision-transformers-for-more","title":"Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead","date":"2021-05-19","arxiv_id":"2105.09121","repositories_listed":0,"syntology":null},{"url":null,"slug":"accent-recognition-with-hybrid-phonetic","title":"Accent Recognition with Hybrid Phonetic Features","date":"2021-05-05","arxiv_id":"2105.01920","repositories_listed":0,"syntology":null},{"url":"/paper/audio-transformers-transformer-architectures","slug":"audio-transformers-transformer-architectures","title":"Audio Transformers","date":"2021-05-01","arxiv_id":"2105.00335","repositories_listed":0,"syntology":null},{"url":null,"slug":"idmt-traffic-an-open-benchmark-dataset-for","title":"IDMT-Traffic: An Open Benchmark Dataset for Acoustic Traffic Monitoring Research","date":"2021-04-28","arxiv_id":"2104.13620","repositories_listed":0,"syntology":null},{"url":null,"slug":"dasee-a-synthetic-database-of-domestic","title":"DASEE A Synthetic Database of Domestic Acoustic Scenes and Events in Dementia Patients Environment","date":"2021-04-27","arxiv_id":"2104.13423","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-feature-ranking-for-sound-based-covid","title":"Audio feature ranking for sound-based COVID-19 patient detection","date":"2021-04-14","arxiv_id":"2104.07128","repositories_listed":0,"syntology":null}],"record_sha256":"ce7fdaa454ccb8be6b54be98a5a070eb4cb3fd3fc9c820d03ef9d04b077d97aa","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}