{"total":47,"rows":[{"id":"2111.10592","title":"Deep Spoken Keyword Spotting: An Overview","created":"2021-11-20","cited_by_count":43,"area":null},{"id":"2306.00238","title":"Bytes Are All You Need: Transformers Operating Directly On File Bytes","created":"2023-05-31","cited_by_count":18,"area":null},{"id":"2206.12513","title":"Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classification","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2309.04842","title":"Leveraging Large Language Models for Exploiting ASR Uncertainty","created":"2023-09-09","cited_by_count":15,"area":null},{"id":"2206.13909","title":"QTI Submission to DCASE 2021: residual normalization for device-imbalanced acoustic scene classification with efficient design","created":"2022-06-28","cited_by_count":10,"area":null},{"id":"2110.01077","title":"Multi-task Voice Activated Framework using Self-supervised Learning","created":"2021-10-03","cited_by_count":9,"area":null},{"id":"2203.16361","title":"Rainbow Keywords: Efficient Incremental Learning for Online Spoken Keyword Spotting","created":"2022-03-30","cited_by_count":8,"area":null},{"id":"2206.13691","title":"Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spotting","created":"2022-06-28","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":"2111.06531","title":"Domain Generalization on Efficient Acoustic Scene Classification using Residual Normalization","created":"2021-11-12","cited_by_count":6,"area":null},{"id":"2202.06483","title":"BiFSMN: Binary Neural Network for Keyword Spotting","created":"2022-02-14","cited_by_count":5,"area":null},{"id":"2402.05960","title":"Phase-driven Domain Generalizable Learning for Nonstationary Time Series","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2207.07429","title":"Continual Learning For On-Device Environmental Sound Classification","created":"2022-07-15","cited_by_count":4,"area":null},{"id":"2210.01719","title":"Learning Temporal Resolution in Spectrogram for Audio Classification","created":"2022-10-04","cited_by_count":4,"area":null},{"id":"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":"2505.11817","title":"AnalyticKWS: Towards Exemplar-Free Analytic Class Incremental Learning for Small-footprint Keyword Spotting","created":"2025-05-17","cited_by_count":4,"area":null},{"id":"2602.18850","title":"When the Inference Meets the Explicitness or Why Multimodality Can Make Us Forget About the Perfect Predictor","created":"2026-02-21","cited_by_count":4,"area":null},{"id":"2210.15425","title":"HEiMDaL: Highly Efficient Method for Detection and Localization of wake-words","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2211.10565","title":"Filterbank Learning for Noise-Robust Small-Footprint Keyword Spotting","created":"2022-11-19","cited_by_count":3,"area":null},{"id":"2309.00140","title":"Improving vision-inspired keyword spotting using dynamic module skipping in streaming conformer encoder","created":"2023-08-31","cited_by_count":3,"area":null},{"id":"2312.17330","title":"Count What You Want: Exemplar Identification and Few-shot Counting of Human Actions in the Wild","created":"2023-12-28","cited_by_count":3,"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":"2602.16442","title":"Hardware-accelerated graph neural networks: an alternative approach for neuromorphic event-based audio classification and keyword spotting on SoC FPGA","created":"2026-02-18","cited_by_count":2,"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":"2310.11379","title":"Robust Wake-Up Word Detection by Two-stage Multi-resolution Ensembles","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2406.06634","title":"Sparse Binarization for Fast Keyword Spotting","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2203.17012","title":"A Temporal-oriented Broadcast ResNet for COVID-19 Detection","created":"2022-03-31","cited_by_count":0,"area":null},{"id":"2302.13435","title":"Scalable Weight Reparametrization for Efficient Transfer Learning","created":"2023-02-26","cited_by_count":0,"area":null},{"id":"2309.00647","title":"Improving Small Footprint Few-shot Keyword Spotting with Supervision on Auxiliary Data","created":"2023-08-31","cited_by_count":0,"area":null},{"id":"2406.02652","title":"RepCNN: Micro-sized, Mighty Models for Wakeword Detection","created":"2024-06-04","cited_by_count":0,"area":null},{"id":"2406.18313","title":"Advancing Airport Tower Command Recognition: Integrating Squeeze-and-Excitation and Broadcasted Residual Learning","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2407.04662","title":"Multitaper mel-spectrograms for keyword spotting","created":"2024-07-05","cited_by_count":0,"area":null},{"id":"2409.12745","title":"Enhancing Synthetic Training Data for Speech Commands: From ASR-Based Filtering to Domain Adaptation in SSL Latent Space","created":"2024-09-19","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":"2503.11373","title":"Exploring Performance-Complexity Trade-Offs in Sound Event Detection Models","created":"2025-03-14","cited_by_count":0,"area":null},{"id":"2503.16862","title":"Improving Acoustic Scene Classification with City Features","created":"2025-03-21","cited_by_count":0,"area":null},{"id":"2507.15545","title":"Data Aware Differentiable Neural Architecture Search for Tiny Keyword Spotting Applications","created":"2025-07-21","cited_by_count":0,"area":null},{"id":"2508.03190","title":"PatchDSU: Uncertainty Modeling for Out of Distribution Generalization in Keyword Spotting","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2510.18036","title":"Transformer Redesign for Late Fusion of Audio-Text Features on Ultra-Low-Power Edge Hardware","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2512.22901","title":"A Neural Network-Based Real-time Casing Collar Recognition System for Downhole Instruments","created":"2025-12-28","cited_by_count":0,"area":null},{"id":"2601.00270","title":"Rectifying Adversarial Examples Using Their Vulnerabilities","created":"2026-01-01","cited_by_count":0,"area":null},{"id":"2601.16158","title":"Domain-Incremental Continual Learning for Robust and Efficient Keyword Spotting in Resource Constrained Systems","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2601.16316","title":"EdgeSpot: Efficient and High-Performance Few-Shot Model for Keyword Spotting","created":"2026-01-22","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":"2609.31699","title":"Normalise or condition? Noise-floor front-ends for on-board keyword spotting under UAV rotor ego-noise","created":"2026-09-19","cited_by_count":0,"area":null}],"next_cursor":null}