{"total":23,"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":"2104.00769","title":"Keyword Transformer: A Self-Attention Model for Keyword Spotting","created":"2021-04-01","cited_by_count":60,"area":null},{"id":"2404.09385","title":"A Large-Scale Evaluation of Speech Foundation Models","created":"2024-04-15","cited_by_count":40,"area":null},{"id":"2303.00733","title":"SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks","created":"2023-03-01","cited_by_count":32,"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":"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":"2308.06472","title":"Flexible Keyword Spotting based on Homogeneous Audio-Text Embedding","created":"2023-08-12","cited_by_count":10,"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":"2310.02973","title":"UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions","created":"2023-10-04","cited_by_count":9,"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":"2206.11239","title":"FedorAS: Federated Architecture Search under system heterogeneity","created":"2022-06-22","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":"2102.08183","title":"Comparison of semi-supervised deep learning algorithms for audio classification","created":"2021-02-16","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":"2205.14329","title":"Speech Augmentation Based Unsupervised Learning for Keyword Spotting","created":"2022-05-28","cited_by_count":1,"area":null},{"id":"2306.07796","title":"Finite Gaussian Neurons: Defending against adversarial attacks by making neural networks say \"I don't know\"","created":"2023-06-13","cited_by_count":1,"area":null},{"id":"2506.17686","title":"Enhancing Few-shot Keyword Spotting Performance through Pre-Trained Self-supervised Speech Models","created":"2025-06-21","cited_by_count":1,"area":null},{"id":"2510.06266","title":"Language models for longitudinal analysis of abusive content in Billboard Music Charts","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2106.00052","title":"Low-Resource Spoken Language Identification Using Self-Attentive Pooling and Deep 1D Time-Channel Separable Convolutions","created":"2021-05-31","cited_by_count":0,"area":null},{"id":"2203.08490","title":"Learning Audio Representations with MLPs","created":"2022-03-16","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":"2411.01839","title":"TriG-NER: Triplet-Grid Framework for Discontinuous Named Entity Recognition","created":"2024-11-04","cited_by_count":0,"area":null},{"id":"2503.12893","title":"Edgeworth Expansion for Semi-hard Triplet Loss","created":"2025-03-17","cited_by_count":0,"area":null}],"next_cursor":null}