{"total":35,"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":"2209.07027","title":"Out-of-Distribution Representation Learning for Time Series Classification","created":"2022-09-15","cited_by_count":31,"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":"2308.02282","title":"DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization","created":"2023-08-04","cited_by_count":24,"area":null},{"id":"2203.09581","title":"SepTr: Separable Transformer for Audio Spectrogram Processing","created":"2022-03-17","cited_by_count":15,"area":null},{"id":"2306.09313","title":"Lexical Speaker Error Correction: Leveraging Language Models for Speaker Diarization Error Correction","created":"2023-06-15","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":"2309.08561","title":"Open-vocabulary Keyword-spotting with Adaptive Instance Normalization","created":"2023-09-13","cited_by_count":8,"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":"2110.03894","title":"Neural Model Reprogramming with Similarity Based Mapping for Low-Resource Spoken Command Recognition","created":"2021-10-08","cited_by_count":3,"area":null},{"id":"2510.21038","title":"Elementary, My Dear Watson: Non-Invasive Neural Keyword Spotting in the LibriBrain Dataset","created":"2025-10-23","cited_by_count":3,"area":null},{"id":"2103.17142","title":"Compressing 1D Time-Channel Separable Convolutions using Sparse Random Ternary Matrices","created":"2021-03-31","cited_by_count":2,"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":"2111.10639","title":"Implicit Acoustic Echo Cancellation for Keyword Spotting and Device-Directed Speech Detection","created":"2021-11-20","cited_by_count":2,"area":null},{"id":"2112.07156","title":"ImportantAug: a data augmentation agent for speech","created":"2021-12-14","cited_by_count":2,"area":null},{"id":"2401.07575","title":"Cascaded Cross-Modal Transformer for Audio-Textual Classification","created":"2024-01-15","cited_by_count":2,"area":null},{"id":"2204.02455","title":"Improving Voice Trigger Detection with Metric Learning","created":"2022-04-05","cited_by_count":1,"area":null},{"id":"2205.14329","title":"Speech Augmentation Based Unsupervised Learning for Keyword Spotting","created":"2022-05-28","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":"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":"2603.21478","title":"TaigiSpeech: A Low-Resource Real-World Speech Intent Dataset and Preliminary Results with Scalable Data Mining In-the-Wild","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2311.16357","title":"Cross Entropy in Deep Learning of Classifiers Is Unnecessary -- ISBE Error is All You Need","created":"2023-11-27","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":"2406.02652","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":"2409.00356","title":"Contrastive Augmentation: An Unsupervised Learning Approach for Keyword Spotting in Speech Technology","created":"2024-08-31","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":"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":"2605.22746","title":"Plug-in Losses for Evidential Deep Learning: A Simplified Framework for Uncertainty Estimation that Includes the Softmax Classifier","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2609.25876","title":"Evaluating the Effectiveness of SechKAN on 1D Data","created":"2026-09-22","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}