{"total":23,"rows":[{"id":"2210.02287","title":"TC-SKNet with GridMask for Low-complexity Classification of Acoustic scene","created":"2022-10-05","cited_by_count":12,"area":null},{"id":"2501.19377","title":"SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions","created":"2025-01-31","cited_by_count":7,"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":"2312.03632","title":"Multimodal Data and Resource Efficient Device-Directed Speech Detection with Large Foundation Models","created":"2023-12-06","cited_by_count":5,"area":null},{"id":"2403.14438","title":"A Multimodal Approach to Device-Directed Speech Detection with Large Language Models","created":"2024-03-21","cited_by_count":5,"area":null},{"id":"2102.13552","title":"The NPU System for the 2020 Personalized Voice Trigger Challenge","created":"2021-02-26","cited_by_count":2,"area":null},{"id":"2207.06920","title":"Sub 8-Bit Quantization of Streaming Keyword Spotting Models for Embedded Chipsets","created":"2022-07-13","cited_by_count":2,"area":null},{"id":"2312.07338","title":"Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification","created":"2023-12-12","cited_by_count":2,"area":null},{"id":"2206.07261","title":"Latency Control for Keyword Spotting","created":"2022-06-15","cited_by_count":1,"area":null},{"id":"2106.04392","title":"Signal Transformer: Complex-valued Attention and Meta-Learning for Signal Recognition","created":"2021-06-05","cited_by_count":0,"area":null},{"id":"2106.07428","title":"Audio Attacks and Defenses against AED Systems -- A Practical Study","created":"2021-06-14","cited_by_count":0,"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":"2207.06423","title":"Wakeword Detection under Distribution Shifts","created":"2022-07-13","cited_by_count":0,"area":null},{"id":"2309.09443","title":"Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter","created":"2023-09-18","cited_by_count":0,"area":null},{"id":"2311.08141","title":"GMTR: Graph Matching Transformers","created":"2023-11-14","cited_by_count":0,"area":null},{"id":"2312.16805","title":"DarkShot: Lighting Dark Images with Low-Compute and High-Quality","created":"2023-12-28","cited_by_count":0,"area":null},{"id":"2401.05431","title":"TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processing","created":"2024-01-06","cited_by_count":0,"area":null},{"id":"2401.05432","title":"TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networks","created":"2024-01-06","cited_by_count":0,"area":null},{"id":"2403.13663","title":"T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Image","created":"2024-03-20","cited_by_count":0,"area":null},{"id":"2408.17101","title":"Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithms","created":"2024-08-30","cited_by_count":0,"area":null},{"id":"2410.11162","title":"Towards General Deepfake Detection with Dynamic Curriculum","created":"2024-10-15","cited_by_count":0,"area":null},{"id":"2410.13409","title":"Attr-Int: A Simple and Effective Entity Alignment Framework for Heterogeneous Knowledge Graphs","created":"2024-10-17","cited_by_count":0,"area":null},{"id":"2507.06486","title":"Mask6D: Masked Pose Priors For 6D Object Pose Estimation","created":"2025-07-09","cited_by_count":0,"area":null}],"next_cursor":null}