{"total":50,"rows":[{"id":"2202.00874","title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","created":"2022-02-02","cited_by_count":176,"area":null},{"id":"2110.09784","title":"SSAST: Self-Supervised Audio Spectrogram Transformer","created":"2021-10-19","cited_by_count":169,"area":null},{"id":"2111.10592","title":"Deep Spoken Keyword Spotting: An Overview","created":"2021-11-20","cited_by_count":43,"area":null},{"id":"2107.00606","title":"Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition","created":"2021-07-01","cited_by_count":24,"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":"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":"2309.14580","title":"CWCL: Cross-Modal Transfer with Continuously Weighted Contrastive Loss","created":"2023-09-26","cited_by_count":12,"area":null},{"id":"2110.15957","title":"Visual Keyword Spotting with Attention","created":"2021-10-29","cited_by_count":11,"area":null},{"id":"2402.04882","title":"LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units","created":"2024-01-20","cited_by_count":11,"area":null},{"id":"2204.03957","title":"Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognition","created":"2022-04-08","cited_by_count":9,"area":null},{"id":"2106.07550","title":"Attention mechanisms and deep learning for machine vision: A survey of the state of the art","created":"2021-06-03","cited_by_count":8,"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":"2309.08561","title":"Open-vocabulary Keyword-spotting with Adaptive Instance Normalization","created":"2023-09-13","cited_by_count":8,"area":null},{"id":"2112.05597","title":"Marvin: an Innovative Omni-Directional Robotic Assistant for Domestic Environments","created":"2021-12-10","cited_by_count":6,"area":null},{"id":"2305.18334","title":"PQA: Exploring the Potential of Product Quantization in DNN Hardware Acceleration","created":"2023-05-25","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":"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":"2206.11239","title":"FedorAS: Federated Architecture Search under system heterogeneity","created":"2022-06-22","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":"2210.01703","title":"Improving Label-Deficient Keyword Spotting Through Self-Supervised Pretraining","created":"2022-10-04","cited_by_count":3,"area":null},{"id":"2110.07749","title":"Attention-Free Keyword Spotting","created":"2021-10-14","cited_by_count":2,"area":null},{"id":"2204.03479","title":"Delta Keyword Transformer: Bringing Transformers to the Edge through Dynamically Pruned Multi-Head Self-Attention","created":"2022-03-20","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":"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":"2511.07883","title":"SpikCommander: A High-performance Spiking Transformer with Multi-view Learning for Efficient Speech Command Recognition","created":"2025-11-11","cited_by_count":2,"area":null},{"id":"2107.09433","title":"Seed Words Based Data Selection for Language Model Adaptation","created":"2021-07-20","cited_by_count":1,"area":null},{"id":"2201.10609","title":"Exploiting Hybrid Models of Tensor-Train Networks for Spoken Command Recognition","created":"2022-01-11","cited_by_count":1,"area":null},{"id":"2204.02455","title":"Improving Voice Trigger Detection with Metric Learning","created":"2022-04-05","cited_by_count":1,"area":null},{"id":"2208.10659","title":"Fall Detection from Audios with Audio Transformers","created":"2022-08-23","cited_by_count":1,"area":null},{"id":"2304.12183","title":"Small-footprint slimmable networks for keyword spotting","created":"2023-04-21","cited_by_count":1,"area":null},{"id":"2305.11360","title":"Differentially Private Adapters for Parameter Efficient Acoustic Modeling","created":"2023-05-19","cited_by_count":1,"area":null},{"id":"2310.17972","title":"EcoLearn: Optimizing the Carbon Footprint of Federated Learning","created":"2023-10-27","cited_by_count":1,"area":null},{"id":"2407.02610","title":"Towards Federated Learning with On-device Training and Communication in 8-bit Floating Point","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2508.06277","title":"Large Language Model Data Generation for Enhanced Intent Recognition in German Speech","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2203.08490","title":"Learning Audio Representations with MLPs","created":"2022-03-16","cited_by_count":0,"area":null},{"id":"2205.12933","title":"Boosting Tail Neural Network for Realtime Custom Keyword Spotting","created":"2022-05-24","cited_by_count":0,"area":null},{"id":"2211.01089","title":"Transformer-based encoder-encoder architecture for Spoken Term Detection","created":"2022-11-02","cited_by_count":0,"area":null},{"id":"2406.02488","title":"Language-Universal Speech Attributes Modeling for Zero-Shot Multilingual Spoken Keyword Recognition","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":"2407.16026","title":"KWT-Tiny: RISC-V Accelerated, Embedded Keyword Spotting Transformer","created":"2024-07-22","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":"2501.11631","title":"Noise-Agnostic Multitask Whisper Training for Reducing False Alarm Errors in Call-for-Help Detection","created":"2025-01-20","cited_by_count":0,"area":null},{"id":"2508.21248","title":"Zero-Shot KWS for Children's Speech using Layer-Wise Features from SSL Models","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2512.17281","title":"LibriVAD: A Scalable Open Dataset with Deep Learning Benchmarks for Voice Activity Detection","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2606.19039","title":"Adaptive Speech-to-Spike Encoding for Spiking Neural Networks","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2608.28640","title":"PromptKWS: A Novel Prompt-Guided Open-Vocabulary Keyword Spotting Framework","created":"2026-08-11","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},{"id":"2609.35005","title":"Sub-Model Short-Term Memory Convolutions for Keyword Spotting Systems on Device","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}