{"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/activity-detection/papers/2","list_of":"/task/activity-detection","task":"Activity Detection","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":2,"pages_in_order":4,"rows_per_page":100,"rows":[101,200],"of":380,"counts":{"archive_papers_tagged":380,"with_a_code_link":75,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":380,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":2,"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/activity-detection","prev":"/task/activity-detection","next":"/task/activity-detection/papers/3","papers":[{"url":null,"slug":"sequence-to-sequence-neural-diarization-with","title":"Sequence-to-Sequence Neural Diarization with Automatic Speaker Detection and Representation","date":"2024-11-21","arxiv_id":"2411.13849","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-flexible-framework-for-grant-free-random","title":"A Flexible Framework for Grant-Free Random Access in Cell-Free Massive MIMO Systems","date":"2024-11-14","arxiv_id":"2411.09328","repositories_listed":0,"syntology":null},{"url":null,"slug":"transferable-adversarial-attacks-against-asr","title":"Transferable Adversarial Attacks against ASR","date":"2024-11-14","arxiv_id":"2411.09220","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-detection-of-non-cooperative-riss-scan","title":"On the Detection of Non-Cooperative RISs: Scan B-Testing via Deep Support Vector Data Description","date":"2024-11-05","arxiv_id":"2411.03237","repositories_listed":0,"syntology":null},{"url":null,"slug":"intelligent-video-recording-optimization","title":"Intelligent Video Recording Optimization using Activity Detection for Surveillance Systems","date":"2024-11-04","arxiv_id":"2411.02632","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-training-of-speaker-embedding-extractor","title":"Joint Training of Speaker Embedding Extractor, Speech and Overlap Detection for Diarization","date":"2024-11-04","arxiv_id":"2411.02165","repositories_listed":0,"syntology":null},{"url":null,"slug":"user-activity-detection-with-delay","title":"User Activity Detection with Delay-Calibration for Asynchronous Massive Random Access","date":"2024-11-04","arxiv_id":"2411.01923","repositories_listed":0,"syntology":null},{"url":null,"slug":"clip-vad-exploiting-vision-language-models","title":"CLIP-VAD: Exploiting Vision-Language Models for Voice Activity Detection","date":"2024-10-18","arxiv_id":"2410.14509","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigation-of-speaker-representation-for","title":"Investigation of Speaker Representation for Target-Speaker Speech Processing","date":"2024-10-15","arxiv_id":"2410.11243","repositories_listed":0,"syntology":null},{"url":null,"slug":"raising-the-bar-ometer-identifying-a-user-s","title":"Raising the Bar(ometer): Identifying a User's Stair and Lift Usage Through Wearable Sensor Data Analysis","date":"2024-09-18","arxiv_id":"2410.02790","repositories_listed":0,"syntology":null},{"url":null,"slug":"m-best-rq-a-multi-channel-speech-foundation","title":"M-BEST-RQ: A Multi-Channel Speech Foundation Model for Smart Glasses","date":"2024-09-17","arxiv_id":"2409.11494","repositories_listed":0,"syntology":null},{"url":null,"slug":"tcg-crest-system-description-for-the-second","title":"TCG CREST System Description for the Second DISPLACE Challenge","date":"2024-09-16","arxiv_id":"2409.15356","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-methodological-survey-of","title":"A Comprehensive Methodological Survey of Human Activity Recognition Across Divers Data Modalities","date":"2024-09-15","arxiv_id":"2409.09678","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-real-time-transcriptions-using","title":"Evaluation of real-time transcriptions using end-to-end ASR models","date":"2024-09-09","arxiv_id":"2409.05674","repositories_listed":0,"syntology":null},{"url":null,"slug":"ntt-multi-speaker-asr-system-for-the-dasr","title":"NTT Multi-Speaker ASR System for the DASR Task of CHiME-8 Challenge","date":"2024-09-09","arxiv_id":"2409.05554","repositories_listed":0,"syntology":null},{"url":null,"slug":"blind-user-activity-detection-for-grant-free","title":"Blind User Activity Detection for Grant-Free Random Access in Cell-Free mMIMO Networks","date":"2024-08-05","arxiv_id":"2408.02359","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-term-conversation-analysis-privacy","title":"Long-Term Conversation Analysis: Privacy-Utility Trade-off under Noise and Reverberation","date":"2024-08-01","arxiv_id":"2408.00382","repositories_listed":0,"syntology":null},{"url":null,"slug":"tokenverse-unifying-speech-and-nlp-tasks-via","title":"TokenVerse: Towards Unifying Speech and NLP Tasks via Transducer-based ASR","date":"2024-07-05","arxiv_id":"2407.04444","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-speech-recognition-for-hindi","title":"Automatic Speech Recognition for Hindi","date":"2024-06-26","arxiv_id":"2406.18135","repositories_listed":0,"syntology":null},{"url":null,"slug":"blending-llms-into-cascaded-speech","title":"Blending LLMs into Cascaded Speech Translation: KIT's Offline Speech Translation System for IWSLT 2024","date":"2024-06-24","arxiv_id":"2406.16777","repositories_listed":0,"syntology":null},{"url":null,"slug":"animalformer-multimodal-vision-framework-for","title":"AnimalFormer: Multimodal Vision Framework for Behavior-based Precision Livestock Farming","date":"2024-06-14","arxiv_id":"2406.09711","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparative-analysis-of-personalized-voice","title":"Comparative Analysis of Personalized Voice Activity Detection Systems: Assessing Real-World Effectiveness","date":"2024-06-12","arxiv_id":"2406.09443","repositories_listed":0,"syntology":null},{"url":null,"slug":"vessel-re-identification-and-activity","title":"Vessel Re-identification and Activity Detection in Thermal Domain for Maritime Surveillance","date":"2024-06-12","arxiv_id":"2406.08294","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-approach-for-user","title":"Deep Learning-Based Approach for User Activity Detection with Grant-Free Random Access in Cell-Free Massive MIMO","date":"2024-06-11","arxiv_id":"2406.07160","repositories_listed":0,"syntology":null},{"url":null,"slug":"precise-analysis-of-covariance","title":"Precise Analysis of Covariance Identifiability for Activity Detection in Grant-Free Random Access","date":"2024-06-03","arxiv_id":"2406.01138","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-real-time-voice-activity-detection-based-on","title":"A Real-Time Voice Activity Detection Based On Lightweight Neural","date":"2024-05-27","arxiv_id":"2405.16797","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-embeddings-with-weakly-supervised","title":"Speaker Embeddings With Weakly Supervised Voice Activity Detection For Efficient Speaker Diarization","date":"2024-05-15","arxiv_id":"2405.09142","repositories_listed":0,"syntology":null},{"url":null,"slug":"whispy-adapting-stt-whisper-models-to-real","title":"Whispy: Adapting STT Whisper Models to Real-Time Environments","date":"2024-05-06","arxiv_id":"2405.03484","repositories_listed":0,"syntology":null},{"url":null,"slug":"activity-detection-for-massive-random-access","title":"Activity Detection for Massive Random Access using Covariance-based Matching Pursuit","date":"2024-05-04","arxiv_id":"2405.02741","repositories_listed":0,"syntology":null},{"url":null,"slug":"fad-sar-a-novel-fishing-activity-detection","title":"FAD-SAR: A Novel Fishing Activity Detection System via Synthetic Aperture Radar Images Based on Deep Learning Method","date":"2024-04-28","arxiv_id":"2404.18245","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-customer-level-fraudulent-activity","title":"A Customer Level Fraudulent Activity Detection Benchmark for Enhancing Machine Learning Model Research and Evaluation","date":"2024-04-23","arxiv_id":"2404.14746","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-3d-lidar-sensors-to-enable","title":"Leveraging 3D LiDAR Sensors to Enable Enhanced Urban Safety and Public Health: Pedestrian Monitoring and Abnormal Activity Detection","date":"2024-04-17","arxiv_id":"2404.10978","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-assisted-parallel-interference","title":"Deep Learning-Assisted Parallel Interference Cancellation for Grant-Free NOMA in Machine-Type Communication","date":"2024-03-12","arxiv_id":"2403.07255","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-speaker-assignment-in-speaker","title":"Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications","date":"2024-03-11","arxiv_id":"2403.06570","repositories_listed":0,"syntology":null},{"url":null,"slug":"svad-a-robust-low-power-and-light-weight","title":"sVAD: A Robust, Low-Power, and Light-Weight Voice Activity Detection with Spiking Neural Networks","date":"2024-03-09","arxiv_id":"2403.05772","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-low-parameter-video-activity","title":"Fast Low-parameter Video Activity Localization in Collaborative Learning Environments","date":"2024-03-02","arxiv_id":"2403.01281","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-activity-delay-detection-and-channel-1","title":"Joint Activity-Delay Detection and Channel Estimation for Asynchronous Massive Random Access: A Free Probability Theory Approach","date":"2024-02-28","arxiv_id":"2402.17996","repositories_listed":0,"syntology":null},{"url":null,"slug":"channel-combination-algorithms-for-robust","title":"Channel-Combination Algorithms for Robust Distant Voice Activity and Overlapped Speech Detection","date":"2024-02-13","arxiv_id":"2402.08312","repositories_listed":0,"syntology":null},{"url":null,"slug":"device-activity-detection-and-channel","title":"Device Activity Detection and Channel Estimation for Millimeter-Wave Massive MIMO","date":"2024-02-07","arxiv_id":"2402.04704","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-computer-vision-based-approach-for-stalking","title":"A Computer Vision Based Approach for Stalking Detection Using a CNN-LSTM-MLP Hybrid Fusion Model","date":"2024-02-05","arxiv_id":"2402.03417","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-user-detection-and-localization-in-near","title":"Joint User Detection and Localization in Near-Field Using Reconfigurable Intelligent Surfaces","date":"2024-02-04","arxiv_id":"2402.02488","repositories_listed":0,"syntology":null},{"url":null,"slug":"clan-a-contrastive-learning-based-novelty","title":"Self-supervised New Activity Detection in Sensor-based Smart Environments","date":"2024-01-17","arxiv_id":"2401.10288","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-input-multi-output-target-speaker-voice","title":"Multi-Input Multi-Output Target-Speaker Voice Activity Detection For Unified, Flexible, and Robust Audio-Visual Speaker Diarization","date":"2024-01-16","arxiv_id":"2401.08052","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-microphone-speaker-separation-and","title":"Single-Microphone Speaker Separation and Voice Activity Detection in Noisy and Reverberant Environments","date":"2024-01-07","arxiv_id":"2401.03448","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-pretraining-for-robust","title":"Self-supervised Pretraining for Robust Personalized Voice Activity Detection in Adverse Conditions","date":"2023-12-27","arxiv_id":"2312.16613","repositories_listed":0,"syntology":null},{"url":null,"slug":"advanced-image-segmentation-techniques-for","title":"Advanced Image Segmentation Techniques for Neural Activity Detection via C-fos Immediate Early Gene Expression","date":"2023-12-13","arxiv_id":"2312.08177","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatiotemporal-event-graphs-for-dynamic-scene","title":"Spatiotemporal Event Graphs for Dynamic Scene Understanding","date":"2023-12-11","arxiv_id":"2312.07621","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-more-practical-group-activity","title":"Towards More Practical Group Activity Detection: A New Benchmark and Model","date":"2023-12-05","arxiv_id":"2312.02878","repositories_listed":0,"syntology":null},{"url":null,"slug":"spire-sies-a-spontaneous-indian-english","title":"SPIRE-SIES: A Spontaneous Indian English Speech Corpus","date":"2023-12-01","arxiv_id":"2312.00698","repositories_listed":0,"syntology":null},{"url":null,"slug":"combatting-human-trafficking-in-the","title":"Combatting Human Trafficking in the Cyberspace: A Natural Language Processing-Based Methodology to Analyze the Language in Online Advertisements","date":"2023-11-22","arxiv_id":"2311.13118","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hybrid-graph-network-for-complex-activity","title":"A Hybrid Graph Network for Complex Activity Detection in Video","date":"2023-10-26","arxiv_id":"2310.17493","repositories_listed":0,"syntology":null},{"url":null,"slug":"device-detection-and-channel-estimation-in","title":"Device Detection and Channel Estimation in MTC with Correlated Activity Pattern","date":"2023-10-23","arxiv_id":"2310.14578","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-driven-target-speech-diarization","title":"Prompt-driven Target Speech Diarization","date":"2023-10-23","arxiv_id":"2310.14823","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-illicit-activity-detection-using","title":"Enhancing Illicit Activity Detection using XAI: A Multimodal Graph-LLM Framework","date":"2023-10-20","arxiv_id":"2310.13787","repositories_listed":0,"syntology":null},{"url":null,"slug":"property-aware-multi-speaker-data-simulation","title":"Property-Aware Multi-Speaker Data Simulation: A Probabilistic Modelling Technique for Synthetic Data Generation","date":"2023-10-18","arxiv_id":"2310.12371","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-mtc-user-activity-detection-and","title":"Hierarchical MTC User Activity Detection and Channel Estimation with Unknown Spatial Covariance","date":"2023-10-16","arxiv_id":"2310.10204","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-online-speaker-diarization-with","title":"End-to-end Online Speaker Diarization with Target Speaker Tracking","date":"2023-10-12","arxiv_id":"2310.08696","repositories_listed":0,"syntology":null},{"url":null,"slug":"vsanet-real-time-speech-enhancement-based-on","title":"VSANet: Real-time Speech Enhancement Based on Voice Activity Detection and Causal Spatial Attention","date":"2023-10-11","arxiv_id":"2310.07295","repositories_listed":0,"syntology":null},{"url":null,"slug":"pp-met-a-real-world-personalized-prompt-based","title":"PP-MeT: a Real-world Personalized Prompt based Meeting Transcription System","date":"2023-09-28","arxiv_id":"2309.16247","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-impact-of-silence-on-speech-anti-spoofing","title":"The Impact of Silence on Speech Anti-Spoofing","date":"2023-09-21","arxiv_id":"2309.11827","repositories_listed":0,"syntology":null},{"url":null,"slug":"effective-abnormal-activity-detection-on","title":"Effective Abnormal Activity Detection on Multivariate Time Series Healthcare Data","date":"2023-09-11","arxiv_id":"2309.05845","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-ear-voice-towards-milli-watt-audio","title":"In-Ear-Voice: Towards Milli-Watt Audio Enhancement With Bone-Conduction Microphones for In-Ear Sensing Platforms","date":"2023-09-05","arxiv_id":"2309.02393","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-dku-msxf-diarization-system-for-the","title":"The DKU-MSXF Diarization System for the VoxCeleb Speaker Recognition Challenge 2023","date":"2023-08-15","arxiv_id":"2308.07595","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-enhanced-system-for-the-detection-and","title":"An enhanced system for the detection and active cancellation of snoring signals","date":"2023-07-31","arxiv_id":"2307.16809","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-microphone-automatic-speech","title":"Multi-microphone Automatic Speech Segmentation in Meetings Based on Circular Harmonics Features","date":"2023-06-07","arxiv_id":"2306.04268","repositories_listed":0,"syntology":null},{"url":null,"slug":"parallel-neurosymbolic-integration-with","title":"Parallel Neurosymbolic Integration with Concordia","date":"2023-06-01","arxiv_id":"2306.00480","repositories_listed":0,"syntology":null},{"url":null,"slug":"svvad-personal-voice-activity-detection-for","title":"SVVAD: Personal Voice Activity Detection for Speaker Verification","date":"2023-05-31","arxiv_id":"2305.19581","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-accurate-low-latency-asr-for","title":"Building Accurate Low Latency ASR for Streaming Voice Search","date":"2023-05-29","arxiv_id":"2305.18596","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-activity-delay-detection-and-channel","title":"Joint Activity-Delay Detection and Channel Estimation for Asynchronous Massive Random Access","date":"2023-05-21","arxiv_id":"2305.12372","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-vad-low-latency-voice-activity","title":"Semantic VAD: Low-Latency Voice Activity Detection for Speech Interaction","date":"2023-05-21","arxiv_id":"2305.12450","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-asynchronous-massive-access","title":"Deep Learning for Asynchronous Massive Access with Data Frame Length Diversity","date":"2023-05-12","arxiv_id":"2305.07278","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-activity-detection-and-channel-3","title":"Joint Activity Detection and Channel Estimation for Clustered Massive Machine Type Communications","date":"2023-05-04","arxiv_id":"2305.02935","repositories_listed":0,"syntology":null},{"url":null,"slug":"cooperative-multi-cell-massive-access-with","title":"Cooperative Multi-Cell Massive Access with Temporally Correlated Activity","date":"2023-04-19","arxiv_id":"2304.09727","repositories_listed":0,"syntology":null},{"url":null,"slug":"array-configuration-agnostic-personal-voice","title":"Array Configuration-Agnostic Personal Voice Activity Detection Based on Spatial Coherence","date":"2023-04-18","arxiv_id":"2304.08887","repositories_listed":0,"syntology":null},{"url":null,"slug":"grant-free-massive-random-access-with","title":"Grant-free Massive Random Access with Retransmission: Receiver Optimization and Performance Analysis","date":"2023-04-12","arxiv_id":"2304.05648","repositories_listed":0,"syntology":null},{"url":null,"slug":"better-together-dialogue-separation-and-voice","title":"Better Together: Dialogue Separation and Voice Activity Detection for Audio Personalization in TV","date":"2023-03-23","arxiv_id":"2303.13453","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-integration-of-speech-separation","title":"End-to-End Integration of Speech Separation and Voice Activity Detection for Low-Latency Diarization of Telephone Conversations","date":"2023-03-21","arxiv_id":"2303.12002","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-processing-framework-to-access-large","title":"A processing framework to access large quantities of whispered speech found in ASMR","date":"2023-03-13","arxiv_id":"2303.07442","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-sub-band-network-for-deep-residual","title":"Multi-Task Sub-Band Network For Deep Residual Echo Suppression","date":"2023-03-11","arxiv_id":"2303.06404","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-transformer-based-end-to-end","title":"Improving Transformer-based End-to-End Speaker Diarization by Assigning Auxiliary Losses to Attention Heads","date":"2023-03-02","arxiv_id":"2303.01192","repositories_listed":0,"syntology":null},{"url":null,"slug":"learnable-frontends-that-do-not-learn","title":"Learnable Frontends that do not Learn: Quantifying Sensitivity to Filterbank Initialisation","date":"2023-02-20","arxiv_id":"2302.10014","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-newsbridge-telecom-sudparis-voxceleb","title":"The Newsbridge -Telecom SudParis VoxCeleb Speaker Recognition Challenge 2022 System Description","date":"2023-01-17","arxiv_id":"2301.07491","repositories_listed":0,"syntology":null},{"url":null,"slug":"kids-kinematics-based-in-activity-detection","title":"KIDS: kinematics-based (in)activity detection and segmentation in a sleep case study","date":"2023-01-04","arxiv_id":"2301.03469","repositories_listed":0,"syntology":null},{"url":null,"slug":"activity-detection-for-grant-free-noma-in","title":"Activity Detection for Grant-Free NOMA in Massive IoT Networks","date":"2022-12-23","arxiv_id":"2301.01274","repositories_listed":0,"syntology":null},{"url":null,"slug":"tackling-the-cocktail-fork-problem-for","title":"Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks","date":"2022-12-14","arxiv_id":"2212.07327","repositories_listed":0,"syntology":null},{"url":null,"slug":"trajectory-user-linking-is-easier-than-you","title":"Trajectory-User Linking Is Easier Than You Think","date":"2022-12-14","arxiv_id":"2212.07081","repositories_listed":0,"syntology":null},{"url":null,"slug":"bc-vad-a-robust-bone-conduction-voice","title":"BC-VAD: A Robust Bone Conduction Voice Activity Detection","date":"2022-12-06","arxiv_id":"2212.02996","repositories_listed":0,"syntology":null},{"url":null,"slug":"proximal-gradient-based-unfolding-for-massive","title":"Proximal Gradient-Based Unfolding for Massive Random Access in IoT Networks","date":"2022-12-04","arxiv_id":"2212.01839","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-estimation-of-clustered-user-activity","title":"Joint Estimation of Clustered User Activity and Correlated Channels with Unknown Covariance in mMTC","date":"2022-11-30","arxiv_id":"2212.00116","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-timescale-event-detection-in","title":"Multi-timescale Event Detection in Nonintrusive Load Monitoring based on MDL Principle","date":"2022-11-19","arxiv_id":"2211.10721","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-using-the-ua-speech-and-torgo-databases-to","title":"On using the UA-Speech and TORGO databases to validate automatic dysarthric speech classification approaches","date":"2022-11-16","arxiv_id":"2211.08833","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-stream-multi-dimensional-convolutional","title":"Two-stream Multi-dimensional Convolutional Network for Real-time Violence Detection","date":"2022-11-08","arxiv_id":"2211.04255","repositories_listed":0,"syntology":null},{"url":null,"slug":"ofdm-based-massive-connectivity-for-leo","title":"OFDM-Based Massive Connectivity for LEO Satellite Internet of Things","date":"2022-10-31","arxiv_id":"2210.17355","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-short-video-speech-recognition","title":"Random Utterance Concatenation Based Data Augmentation for Improving Short-video Speech Recognition","date":"2022-10-28","arxiv_id":"2210.15876","repositories_listed":0,"syntology":null},{"url":null,"slug":"target-speaker-voice-activity-detection-via","title":"Target-Speaker Voice Activity Detection via Sequence-to-Sequence Prediction","date":"2022-10-28","arxiv_id":"2210.16127","repositories_listed":0,"syntology":null},{"url":null,"slug":"tsup-speaker-diarization-system-for","title":"TSUP Speaker Diarization System for Conversational Short-phrase Speaker Diarization Challenge","date":"2022-10-26","arxiv_id":"2210.14653","repositories_listed":0,"syntology":null},{"url":null,"slug":"intel-labs-at-ego4d-challenge-2022-a-better","title":"Intel Labs at Ego4D Challenge 2022: A Better Baseline for Audio-Visual Diarization","date":"2022-10-14","arxiv_id":"2210.07764","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-dku-dukeece-diarization-system-for-the","title":"The DKU-DukeECE Diarization System for the VoxCeleb Speaker Recognition Challenge 2022","date":"2022-10-04","arxiv_id":"2210.01677","repositories_listed":0,"syntology":null},{"url":null,"slug":"learnable-acoustic-frontends-in-bird-activity","title":"Learnable Acoustic Frontends in Bird Activity Detection","date":"2022-10-03","arxiv_id":"2210.00889","repositories_listed":0,"syntology":null},{"url":null,"slug":"signed-latent-factors-for-spamming-activity","title":"Signed Latent Factors for Spamming Activity Detection","date":"2022-09-28","arxiv_id":"2209.13814","repositories_listed":0,"syntology":null}],"record_sha256":"2b4421df14518cdbb754937d783ad1eae216cb2a3d8c36ca91305278b07c62df","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}