{"total":45,"rows":[{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643,"area":null},{"id":"2104.00769","title":"Keyword Transformer: A Self-Attention Model for Keyword Spotting","created":"2021-04-01","cited_by_count":60,"area":null},{"id":"2106.04140","title":"Broadcasted Residual Learning for Efficient Keyword Spotting","created":"2021-06-08","cited_by_count":48,"area":null},{"id":"2111.10592","title":"Deep Spoken Keyword Spotting: An Overview","created":"2021-11-20","cited_by_count":43,"area":null},{"id":"2101.04792","title":"Learning Efficient Representations for Keyword Spotting with Triplet Loss","created":"2021-01-12","cited_by_count":24,"area":null},{"id":"2401.03078","title":"StreamVC: Real-Time Low-Latency Voice Conversion","created":"2024-01-05","cited_by_count":15,"area":null},{"id":"2311.08323","title":"The taste of IPA: Towards open-vocabulary keyword spotting and forced alignment in any language","created":"2023-11-14","cited_by_count":14,"area":null},{"id":"2106.02443","title":"Teaching keyword spotters to spot new keywords with limited examples","created":"2021-06-04","cited_by_count":9,"area":null},{"id":"2306.02161","title":"Few-Shot Open-Set Learning for On-Device Customization of KeyWord Spotting Systems","created":"2023-06-03","cited_by_count":9,"area":null},{"id":"2204.07064","title":"Streamable Neural Audio Synthesis With Non-Causal Convolutions","created":"2022-04-14","cited_by_count":7,"area":null},{"id":"2206.13708","title":"Personalized Keyword Spotting through Multi-task Learning","created":"2022-06-28","cited_by_count":7,"area":null},{"id":"2408.12481","title":"Self-Learning for Personalized Keyword Spotting on Ultra-Low-Power Audio Sensors","created":"2024-08-22","cited_by_count":7,"area":null},{"id":"2508.01915","title":"EgoTrigger: Toward Audio-Driven Image Capture for Human Memory Enhancement in All-Day Energy-Efficient Smart Glasses","created":"2025-08-03","cited_by_count":6,"area":null},{"id":"2108.04051","title":"A Streamwise GAN Vocoder for Wideband Speech Coding at Very Low Bit Rate","created":"2021-08-09","cited_by_count":5,"area":null},{"id":"2109.14725","title":"Tiny-CRNN: Streaming Wakeword Detection In A Low Footprint Setting","created":"2021-09-29","cited_by_count":5,"area":null},{"id":"2109.10252","title":"Audiomer: A Convolutional Transformer For Keyword Spotting","created":"2021-09-21","cited_by_count":4,"area":null},{"id":"2206.08864","title":"Avoid Overfitting User Specific Information in Federated Keyword Spotting","created":"2022-06-17","cited_by_count":4,"area":null},{"id":"2211.04635","title":"LiCo-Net: Linearized Convolution Network for Hardware-efficient Keyword Spotting","created":"2022-11-09","cited_by_count":4,"area":null},{"id":"2211.06987","title":"BiFSMNv2: Pushing Binary Neural Networks for Keyword Spotting to Real-Network Performance","created":"2022-11-13","cited_by_count":4,"area":null},{"id":"2508.05207","title":"SpectroStream: A Versatile Neural Codec for General Audio","created":"2025-08-07","cited_by_count":4,"area":null},{"id":"2209.00934","title":"TB or not TB? Acoustic cough analysis for tuberculosis classification","created":"2022-09-02","cited_by_count":3,"area":null},{"id":"2505.24852","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2106.02738","title":"Encoder-Decoder Neural Architecture Optimization for Keyword Spotting","created":"2021-06-04","cited_by_count":2,"area":null},{"id":"2110.07749","title":"Attention-Free Keyword Spotting","created":"2021-10-14","cited_by_count":2,"area":null},{"id":"2304.03416","title":"To Wake-up or Not to Wake-up: Reducing Keyword False Alarm by Successive Refinement","created":"2023-04-06","cited_by_count":2,"area":null},{"id":"2407.16840","title":"Synth4Kws: Synthesized Speech for User Defined Keyword Spotting in Low Resource Environments","created":"2024-07-23","cited_by_count":2,"area":null},{"id":"2410.16647","title":"GE2E-KWS: Generalized End-to-End Training and Evaluation for Zero-shot Keyword Spotting","created":"2024-10-22","cited_by_count":2,"area":null},{"id":"2202.02361","title":"A Fast Network Exploration Strategy to Profile Low Energy Consumption for Keyword Spotting","created":"2022-02-04","cited_by_count":1,"area":null},{"id":"2210.13567","title":"I see what you hear: a vision-inspired method to localize words","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2303.07486","title":"Guided Speech Enhancement Network","created":"2023-03-13","cited_by_count":1,"area":null},{"id":"2401.08864","title":"Binaural Angular Separation Network","created":"2024-01-16","cited_by_count":1,"area":null},{"id":"2408.13355","title":"Disentangled Training with Adversarial Examples For Robust Small-footprint Keyword Spotting","created":"2024-08-23","cited_by_count":1,"area":null},{"id":"2503.11562","title":"Designing Neural Synthesizers for Low-Latency Interaction","created":"2025-03-14","cited_by_count":1,"area":null},{"id":"2601.17690","title":"Segment Length Matters: A Study of Segment Lengths on Audio Fingerprinting Performance","created":"2026-01-25","cited_by_count":1,"area":null},{"id":"2202.08509","title":"A Study of Designing Compact Audio-Visual Wake Word Spotting System Based on Iterative Fine-Tuning in Neural Network Pruning","created":"2022-02-17","cited_by_count":0,"area":null},{"id":"2305.05110","title":"Semi-Supervised Federated Learning for Keyword Spotting","created":"2023-05-09","cited_by_count":0,"area":null},{"id":"2308.16570","title":"MONDEO: Multistage Botnet Detection","created":"2023-08-31","cited_by_count":0,"area":null},{"id":"2311.16977","title":"Bidirectional Reactive Programming for Machine Learning","created":"2023-11-28","cited_by_count":0,"area":null},{"id":"2312.16228","title":"Deformable Audio Transformer for Audio Event Detection","created":"2023-12-24","cited_by_count":0,"area":null},{"id":"2405.01739","title":"Enhancing User Experience in On-Device Machine Learning with Gated Compression Layers","created":"2024-05-02","cited_by_count":0,"area":null},{"id":"2411.14489","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","created":"2024-11-20","cited_by_count":0,"area":null},{"id":"2501.03523","title":"Vocal Tract Length Warped Features for Spoken Keyword Spotting","created":"2025-01-07","cited_by_count":0,"area":null},{"id":"2603.18023","title":"PCOV-KWS: Multi-task Learning for Personalized Customizable Open Vocabulary Keyword Spotting","created":"2026-03-05","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":"2607.21797","title":"Relaxed activation analysis of dataflow networks - A clock calculus for machine learning and real-time scheduling","created":"2026-07-23","cited_by_count":0,"area":null}],"next_cursor":null}