{"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/3","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":3,"pages_in_order":4,"rows_per_page":100,"rows":[201,300],"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/papers/2","next":"/task/activity-detection/papers/4","papers":[{"url":null,"slug":"joint-speech-activity-and-overlap-detection","title":"Joint Speech Activity and Overlap Detection with Multi-Exit Architecture","date":"2022-09-24","arxiv_id":"2209.11906","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-kriston-ai-system-for-the-voxceleb","title":"The Kriston AI System for the VoxCeleb Speaker Recognition Challenge 2022","date":"2022-09-23","arxiv_id":"2209.11433","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-domain-voice-activity-detection-with","title":"Cross-domain Voice Activity Detection with Self-Supervised Representations","date":"2022-09-22","arxiv_id":"2209.11061","repositories_listed":0,"syntology":null},{"url":null,"slug":"gist-aiter-system-for-the-diarization-task-of","title":"GIST-AiTeR System for the Diarization Task of the 2022 VoxCeleb Speaker Recognition Challenge","date":"2022-09-21","arxiv_id":"2209.10357","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":null,"slug":"target-speaker-voice-activity-detection-with-1","title":"Target Speaker Voice Activity Detection with Transformers and Its Integration with End-to-End Neural Diarization","date":"2022-08-27","arxiv_id":"2208.13085","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-target-speaker-voice-activity","title":"Online Target Speaker Voice Activity Detection for Speaker Diarization","date":"2022-07-13","arxiv_id":"2207.05920","repositories_listed":0,"syntology":null},{"url":"/paper/fine-grained-activities-of-people-worldwide","slug":"fine-grained-activities-of-people-worldwide","title":"Fine-grained Activities of People Worldwide","date":"2022-07-11","arxiv_id":"2207.05182","repositories_listed":0,"syntology":null},{"url":null,"slug":"tandem-multitask-training-of-speaker","title":"Tandem Multitask Training of Speaker Diarisation and Speech Recognition for Meeting Transcription","date":"2022-07-08","arxiv_id":"2207.03852","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-aiot-enabled-autonomous-dementia","title":"An AIoT-enabled Autonomous Dementia Monitoring System","date":"2022-07-02","arxiv_id":"2207.00804","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-channel-end-to-end-neural-network-for","title":"Multi-channel end-to-end neural network for speech enhancement, source localization, and voice activity detection","date":"2022-06-20","arxiv_id":"2206.09728","repositories_listed":0,"syntology":null},{"url":null,"slug":"simultaneous-speech-extraction-for-multiple","title":"Simultaneous Speech Extraction for Multiple Target Speakers under the Meeting Scenarios","date":"2022-06-17","arxiv_id":"2206.08525","repositories_listed":0,"syntology":null},{"url":null,"slug":"ris-assisted-device-activity-detection-with","title":"RIS Assisted Device Activity Detection with Statistical Channel State Information","date":"2022-06-14","arxiv_id":"2206.06805","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-aided-active-user-detection-with-a-user","title":"Data-aided Active User Detection with a User Activity Extraction Network for Grant-free SCMA Systems","date":"2022-05-22","arxiv_id":"2205.10780","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-boosting-algorithm-for-positive-unlabeled","title":"A Boosting Algorithm for Positive-Unlabeled Learning","date":"2022-05-19","arxiv_id":"2205.09485","repositories_listed":0,"syntology":null},{"url":null,"slug":"double-sided-information-aided-temporal","title":"Double-Sided Information Aided Temporal-Correlated Massive Access","date":"2022-05-16","arxiv_id":"2205.07494","repositories_listed":0,"syntology":null},{"url":null,"slug":"activity-detection-in-long-surgical-videos","title":"An Empirical Study on Activity Recognition in Long Surgical Videos","date":"2022-05-05","arxiv_id":"2205.02805","repositories_listed":0,"syntology":null},{"url":null,"slug":"ultra-sensitive-flexible-sponge-sensor-array","title":"Ultra-sensitive Flexible Sponge-Sensor Array for Muscle Activities Detection and Human Limb Motion Recognition","date":"2022-04-30","arxiv_id":"2205.03238","repositories_listed":0,"syntology":null},{"url":"/paper/ada-vad-unpaired-adversarial-domain","slug":"ada-vad-unpaired-adversarial-domain","title":"ADA-VAD: Unpaired Adversarial Domain Adaptation for Noise-Robust Voice Activity Detection","date":"2022-04-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"anomalous-sound-detection-based-on-machine","title":"Anomalous Sound Detection Based on Machine Activity Detection","date":"2022-04-15","arxiv_id":"2204.07353","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-speech-tools-for-helping","title":"Automated speech tools for helping communities process restricted-access corpora for language revival efforts","date":"2022-04-15","arxiv_id":"2204.07272","repositories_listed":0,"syntology":null},{"url":null,"slug":"personal-vad-2-0-optimizing-personal-voice","title":"Personal VAD 2.0: Optimizing Personal Voice Activity Detection for On-Device Speech Recognition","date":"2022-04-08","arxiv_id":"2204.03793","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-encrypted-traffic","title":"Deep Learning for Encrypted Traffic Classification and Unknown Data Detection","date":"2022-03-25","arxiv_id":"2203.15501","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-attention-detection-using-am-fm","title":"Human Attention Detection Using AM-FM Representations","date":"2022-03-09","arxiv_id":"2203.07093","repositories_listed":0,"syntology":null},{"url":null,"slug":"pami-ad-an-activity-detector-exploiting-part","title":"PAMI-AD: An Activity Detector Exploiting Part-attention and Motion Information in Surveillance Videos","date":"2022-03-08","arxiv_id":"2203.03796","repositories_listed":0,"syntology":null},{"url":null,"slug":"random-access-with-massive-mimo-otfs-in-leo","title":"Random Access with Massive MIMO-OTFS in LEO Satellite Communications","date":"2022-02-26","arxiv_id":"2202.13058","repositories_listed":0,"syntology":null},{"url":null,"slug":"vadoi-voice-activity-detection-overlapping","title":"VADOI:Voice-Activity-Detection Overlapping Inference For End-to-end Long-form Speech Recognition","date":"2022-02-22","arxiv_id":"2202.10593","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-privacy-utility-trade-off-against","title":"Active Privacy-Utility Trade-off Against Inference in Time-Series Data Sharing","date":"2022-02-11","arxiv_id":"2202.05833","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-ustc-ximalaya-system-for-the-icassp-2022","title":"The USTC-Ximalaya system for the ICASSP 2022 multi-channel multi-party meeting transcription (M2MeT) challenge","date":"2022-02-10","arxiv_id":"2202.04855","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-channel-attention-based-target-speaker","title":"Cross-Channel Attention-Based Target Speaker Voice Activity Detection: Experimental Results for M2MeT Challenge","date":"2022-02-06","arxiv_id":"2202.02687","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-cuhk-tencent-speaker-diarization-system","title":"The CUHK-TENCENT speaker diarization system for the ICASSP 2022 multi-channel multi-party meeting transcription challenge","date":"2022-02-04","arxiv_id":"2202.01986","repositories_listed":0,"syntology":null},{"url":null,"slug":"argus-robust-real-time-activity-detection-for","title":"Argus++: Robust Real-time Activity Detection for Unconstrained Video Streams with Overlapping Cube Proposals","date":"2022-01-14","arxiv_id":"2201.05290","repositories_listed":0,"syntology":null},{"url":"/paper/egocentric-deep-multi-channel-audio-visual","slug":"egocentric-deep-multi-channel-audio-visual","title":"Egocentric Deep Multi-Channel Audio-Visual Active Speaker Localization","date":"2022-01-06","arxiv_id":"2201.01928","repositories_listed":0,"syntology":null},{"url":null,"slug":"merry-go-round-rotate-a-frame-and-fool-a-dnn","title":"Merry Go Round: Rotate a Frame and Fool a DNN","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"binary-image-skeletonization-using-2-stage-u","title":"Binary Image Skeletonization Using 2-Stage U-Net","date":"2021-12-22","arxiv_id":"2112.11824","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resource-species-agnostic-bird-activity","title":"Low Resource Species Agnostic Bird Activity Detection","date":"2021-12-16","arxiv_id":"2112.09042","repositories_listed":0,"syntology":null},{"url":null,"slug":"user-activity-detection-and-channel-1","title":"User Activity Detection and Channel Estimation of Spatially Correlated Channels via AMP in Massive MTC","date":"2021-12-08","arxiv_id":"2112.04295","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-proximal-operator-methods-for","title":"Learning Proximal Operator Methods for Massive Connectivity in IoT Networks","date":"2021-12-06","arxiv_id":"2112.02830","repositories_listed":0,"syntology":null},{"url":null,"slug":"reformulating-zero-shot-action-recognition","title":"Reformulating Zero-shot Action Recognition for Multi-label Actions","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"user-activity-detection-for-irregular","title":"User Activity Detection for Irregular Repetition Slotted Aloha based MMTC","date":"2021-11-11","arxiv_id":"2111.06140","repositories_listed":0,"syntology":null},{"url":null,"slug":"access-delay-constrained-activity-detection","title":"Access Delay Constrained Activity Detection in Massive Random Access","date":"2021-11-04","arxiv_id":"2111.03051","repositories_listed":0,"syntology":null},{"url":null,"slug":"power-efficient-analog-features-for-audio","title":"PEAF: Learnable Power Efficient Analog Acoustic Features for Audio Recognition","date":"2021-10-07","arxiv_id":"2110.03715","repositories_listed":0,"syntology":null},{"url":null,"slug":"transcribe-to-diarize-neural-speaker","title":"Transcribe-to-Diarize: Neural Speaker Diarization for Unlimited Number of Speakers using End-to-End Speaker-Attributed ASR","date":"2021-10-07","arxiv_id":"2110.03151","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-action-detection-in","title":"Deep Learning-based Action Detection in Untrimmed Videos: A Survey","date":"2021-09-30","arxiv_id":"2110.00111","repositories_listed":0,"syntology":null},{"url":"/paper/the-vvad-lrs3-dataset-for-visual-voice","slug":"the-vvad-lrs3-dataset-for-visual-voice","title":"The VVAD-LRS3 Dataset for Visual Voice Activity Detection","date":"2021-09-28","arxiv_id":"2109.13789","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-dku-dukeece-lenovo-system-for-the","title":"The DKU-DukeECE-Lenovo System for the Diarization Task of the 2021 VoxCeleb Speaker Recognition Challenge","date":"2021-09-05","arxiv_id":"2109.02002","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparse-signal-processing-for-massive","title":"Sparse Signal Processing for Massive Connectivity via Mixed-Integer Programming","date":"2021-08-20","arxiv_id":"2108.09116","repositories_listed":0,"syntology":null},{"url":null,"slug":"target-speaker-voice-activity-detection-with","title":"Target-speaker Voice Activity Detection with Improved I-Vector Estimation for Unknown Number of Speaker","date":"2021-08-07","arxiv_id":"2108.03342","repositories_listed":0,"syntology":null},{"url":null,"slug":"vad-free-streaming-hybrid-ctc-attention-asr","title":"VAD-free Streaming Hybrid CTC/Attention ASR for Unsegmented Recording","date":"2021-07-15","arxiv_id":"2107.07509","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-activity-detection-channel-estimation","title":"Joint Activity Detection, Channel Estimation, and Data Decoding for Grant-free Massive Random Access","date":"2021-07-12","arxiv_id":"2107.05246","repositories_listed":0,"syntology":null},{"url":null,"slug":"voice-activity-detection-for-transient-noisy","title":"Voice Activity Detection for Transient Noisy Environment Based on Diffusion Nets","date":"2021-06-25","arxiv_id":"2106.13763","repositories_listed":0,"syntology":null},{"url":null,"slug":"dealing-with-training-and-test-segmentation","title":"Dealing with training and test segmentation mismatch: FBK@IWSLT2021","date":"2021-06-23","arxiv_id":"2106.12607","repositories_listed":0,"syntology":null},{"url":null,"slug":"eml-online-speech-activity-detection-for-the","title":"EML Online Speech Activity Detection for the Fearless Steps Challenge Phase-III","date":"2021-06-21","arxiv_id":"2106.11075","repositories_listed":0,"syntology":null},{"url":null,"slug":"algorithm-unrolling-for-massive-access-via","title":"Algorithm Unrolling for Massive Access via Deep Neural Network with Theoretical Guarantee","date":"2021-06-19","arxiv_id":"2106.10426","repositories_listed":0,"syntology":null},{"url":"/paper/jrdb-act-a-large-scale-multi-modal-dataset","slug":"jrdb-act-a-large-scale-multi-modal-dataset","title":"JRDB-Act: A Large-scale Dataset for Spatio-temporal Action, Social Group and Activity Detection","date":"2021-06-16","arxiv_id":"2106.08827","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-channel-estimation-and-device-activity","title":"Joint Channel Estimation and Device Activity Detection in Heterogeneous Networks","date":"2021-05-27","arxiv_id":"2105.13118","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-coordinate-descent-via-active","title":"Accelerating Coordinate Descent via Active Set Selection for Device Activity Detection for Multi-Cell Massive Random Access","date":"2021-04-27","arxiv_id":"2104.12984","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-activity-detection-and-data-decoding-in","title":"Joint Activity Detection and Data Decoding in Massive Random Access via a Turbo Receiver","date":"2021-04-26","arxiv_id":"2104.12443","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-voice-activity-detection-hybrid-audio","title":"Beyond Voice Activity Detection: Hybrid Audio Segmentation for Direct Speech Translation","date":"2021-04-23","arxiv_id":"2104.11710","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-correlation-aware-compressed-sensing","title":"Spatial Correlation Aware Compressed Sensing for User Activity Detection and Channel Estimation in Massive MTC","date":"2021-04-17","arxiv_id":"2104.08508","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatiotemporal-deformable-models-for-long","title":"Spatiotemporal Deformable Scene Graphs for Complex Activity Detection","date":"2021-04-16","arxiv_id":"2104.08194","repositories_listed":0,"syntology":null},{"url":null,"slug":"improvement-of-noise-robust-single-channel","title":"Improvement of Noise-Robust Single-Channel Voice Activity Detection with Spatial Pre-processing","date":"2021-04-12","arxiv_id":"2104.05481","repositories_listed":0,"syntology":null},{"url":null,"slug":"early-detection-of-in-memory-malicious","title":"Early Detection of In-Memory Malicious Activity based on Run-time Environmental Features","date":"2021-03-30","arxiv_id":"2103.16029","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparse-activity-discovery-in-energy","title":"Sparse Activity Discovery in Energy Constrained Multi-Cluster IoT Networks Using Group Testing","date":"2021-03-30","arxiv_id":"2103.16174","repositories_listed":0,"syntology":null},{"url":null,"slug":"ustc-nelslip-system-description-for-dihard","title":"USTC-NELSLIP System Description for DIHARD-III Challenge","date":"2021-03-19","arxiv_id":"2103.10661","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-reweighted-algorithms-for-joint","title":"Iterative Reweighted Algorithms for Joint User Identification and Channel Estimation in Spatially Correlated Massive MTC","date":"2021-03-15","arxiv_id":"2103.08242","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-ultra-low-power-rnn-classifier-for-always","title":"An Ultra-low Power RNN Classifier for Always-On Voice Wake-Up Detection Robust to Real-World Scenarios","date":"2021-03-08","arxiv_id":"2103.04792","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-running-speech-recognizer-an-end-to-end","title":"Incorporating VAD into ASR System by Multi-task Learning","date":"2021-03-02","arxiv_id":"2103.01661","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-dereverberation-beamforming-and","title":"End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend","date":"2021-02-23","arxiv_id":"2102.11525","repositories_listed":0,"syntology":null},{"url":null,"slug":"supporting-more-active-users-for-massive","title":"Supporting More Active Users for Massive Access via Data-assisted Activity Detection","date":"2021-02-17","arxiv_id":"2102.08621","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-training-targets-for-noise-robust-voice","title":"On training targets for noise-robust voice activity detection","date":"2021-02-15","arxiv_id":"2102.07445","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-efficient-active-set-algorithm-for","title":"An Efficient Active Set Algorithm for Covariance Based Joint Data and Activity Detection for Massive Random Access with Massive MIMO","date":"2021-02-06","arxiv_id":"2102.03490","repositories_listed":0,"syntology":null},{"url":"/paper/anomalous-event-recognition-in-videos-based","slug":"anomalous-event-recognition-in-videos-based","title":"Anomalous Event Recognition in Videos Based on Joint Learningof Motion and Appearance with Multiple Ranking Measures","date":"2021-02-02","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"quantum-learning-based-nonrandom-superimposed","title":"Quantum Learning Based Nonrandom Superimposed Coding for Secure Wireless Access in 5G URLLC","date":"2021-01-24","arxiv_id":"2101.09712","repositories_listed":0,"syntology":null},{"url":null,"slug":"activity-recognition-with-moving-cameras-and","title":"Activity Recognition with Moving Cameras and Few Training Examples: Applications for Detection of Autism-Related Headbanging","date":"2021-01-10","arxiv_id":"2101.03478","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-user-activity-and-data-detection-in","title":"Joint User Activity and Data Detection in Grant-Free NOMA using Generative Neural Networks","date":"2021-01-07","arxiv_id":"2101.02324","repositories_listed":0,"syntology":null},{"url":"/paper/meva-a-large-scale-multiview-multimodal-video","slug":"meva-a-large-scale-multiview-multimodal-video","title":"MEVA: A Large-Scale Multiview, Multimodal Video Dataset for Activity Detection","date":"2020-12-02","arxiv_id":"2012.00914","repositories_listed":0,"syntology":null},{"url":null,"slug":"nudge-accelerating-overdue-pull-requests","title":"Nudge: Accelerating Overdue Pull Requests Towards Completion","date":"2020-11-25","arxiv_id":"2011.12468","repositories_listed":0,"syntology":null},{"url":"/paper/voxlingua107-a-dataset-for-spoken-language","slug":"voxlingua107-a-dataset-for-spoken-language","title":"VOXLINGUA107: A DATASET FOR SPOKEN LANGUAGE RECOGNITION","date":"2020-11-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-time-frequency-based-suspicious-activity","title":"A Time-Frequency based Suspicious Activity Detection for Anti-Money Laundering","date":"2020-11-17","arxiv_id":"2011.08492","repositories_listed":0,"syntology":null},{"url":null,"slug":"activity-detection-and-modeling-using-smart","title":"Activity Detection And Modeling Using Smart Meter Data: Concept And Case Studies","date":"2020-10-26","arxiv_id":"2010.13288","repositories_listed":0,"syntology":null},{"url":null,"slug":"marblenet-deep-1d-time-channel-separable","title":"MarbleNet: Deep 1D Time-Channel Separable Convolutional Neural Network for Voice Activity Detection","date":"2020-10-26","arxiv_id":"2010.13886","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-multi-channel-features-for-speaker","title":"Multi-Channel Speaker Verification for Single and Multi-talker Speech","date":"2020-10-23","arxiv_id":"2010.12692","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-enhancement-aided-end-to-end-multi","title":"Speech enhancement aided end-to-end multi-task learning for voice activity detection","date":"2020-10-23","arxiv_id":"2010.12484","repositories_listed":0,"syntology":null},{"url":null,"slug":"combination-of-deep-speaker-embeddings-for","title":"Combination of Deep Speaker Embeddings for Diarisation","date":"2020-10-22","arxiv_id":"2010.12025","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-huawei-speaker-diarisation-system-for-the","title":"The HUAWEI Speaker Diarisation System for the VoxCeleb Speaker Diarisation Challenge","date":"2020-10-22","arxiv_id":"2010.11657","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-efficient-algorithm-for-device-detection","title":"An Efficient Algorithm for Device Detection and Channel Estimation in Asynchronous IoT Systems","date":"2020-10-20","arxiv_id":"2010.09979","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-sound-of-silence-in-eeg-cognitive-voice","title":"The \"Sound of Silence\" in EEG -- Cognitive voice activity detection","date":"2020-10-12","arxiv_id":"2010.05497","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-deep-learning-framework-for-short","title":"A Unified Deep Learning Framework for Short-Duration Speaker Verification in Adverse Environments","date":"2020-10-06","arxiv_id":"2010.02477","repositories_listed":0,"syntology":null},{"url":null,"slug":"grant-free-access-via-bilinear-inference-for","title":"Grant-Free Access via Bilinear Inference for Cell-Free MIMO with Low-Coherent Pilots","date":"2020-09-27","arxiv_id":"2009.12863","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-visual-voice-activity-detection-with","title":"Learning Visual Voice Activity Detection with an Automatically Annotated Dataset","date":"2020-09-23","arxiv_id":"2009.11204","repositories_listed":0,"syntology":null},{"url":null,"slug":"trecvid-2019-an-evaluation-campaign-to","title":"TRECVID 2019: An Evaluation Campaign to Benchmark Video Activity Detection, Video Captioning and Matching, and Video Search & Retrieval","date":"2020-09-21","arxiv_id":"2009.09984","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-multitask-loss-function-for-audio-event","title":"On Multitask Loss Function for Audio Event Detection and Localization","date":"2020-09-11","arxiv_id":"2009.05527","repositories_listed":0,"syntology":null},{"url":null,"slug":"massive-machine-type-communication-pilot","title":"Massive Machine Type Communication Pilot-Hopping Sequence Detection Architectures Based on Non-Negative Least Squares for Grant-Free Random Access","date":"2020-09-04","arxiv_id":"2009.02089","repositories_listed":0,"syntology":null},{"url":null,"slug":"segcodenet-color-coded-segmentation-masks-for","title":"SegCodeNet: Color-Coded Segmentation Masks for Activity Detection from Wearable Cameras","date":"2020-08-19","arxiv_id":"2008.08452","repositories_listed":0,"syntology":null},{"url":null,"slug":"mlnet-an-adaptive-multiple-receptive-field","title":"MLNET: An Adaptive Multiple Receptive-field Attention Neural Network for Voice Activity Detection","date":"2020-08-13","arxiv_id":"2008.05650","repositories_listed":0,"syntology":null},{"url":null,"slug":"jointly-sparse-signal-recovery-and-support","title":"Jointly Sparse Signal Recovery and Support Recovery via Deep Learning with Applications in MIMO-based Grant-Free Random Access","date":"2020-08-05","arxiv_id":"2008.01992","repositories_listed":0,"syntology":null},{"url":null,"slug":"this-is-houston-say-again-please-the-behavox","title":"\"This is Houston. Say again, please\". The Behavox system for the Apollo-11 Fearless Steps Challenge (phase II)","date":"2020-08-04","arxiv_id":"2008.01504","repositories_listed":0,"syntology":null},{"url":null,"slug":"statistical-and-neural-network-based-speech","title":"Statistical and Neural Network Based Speech Activity Detection in Non-Stationary Acoustic Environments","date":"2020-07-28","arxiv_id":"2005.09913","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-afrl-iwslt-2020-systems-work-from-home","title":"The AFRL IWSLT 2020 Systems: Work-From-Home Edition","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"3d99f6ac65aaa14f158152748202f434b28320aa469cfdaa76971ac53fc99830","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}