{"total":52,"rows":[{"id":"2307.15220","title":"Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures","created":"2023-07-27","cited_by_count":68,"area":null},{"id":"2306.11503","title":"The Age of Synthetic Realities: Challenges and Opportunities","created":"2023-06-09","cited_by_count":15,"area":null},{"id":"2309.07438","title":"Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challenges","created":"2023-09-14","cited_by_count":14,"area":null},{"id":"2404.00569","title":"CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models","created":"2024-03-31","cited_by_count":13,"area":"diffusion"},{"id":"2306.01432","title":"Audio-Visual Speech Enhancement with Score-Based Generative Models","created":"2023-06-02","cited_by_count":12,"area":"diffusion"},{"id":"2305.18028","title":"ADAPTERMIX: Exploring the Efficacy of Mixture of Adapters for Low-Resource TTS Adaptation","created":"2023-05-29","cited_by_count":7,"area":null},{"id":"2402.15993","title":"Model Compression Method for S4 with Diagonal State Space Layers using Balanced Truncation","created":"2024-02-25","cited_by_count":7,"area":"ssm"},{"id":"2505.17613","title":"MMMG: a Comprehensive and Reliable Benchmark for Multitask Multimodal Generation","created":"2025-05-23","cited_by_count":6,"area":null},{"id":"2506.12879","title":"Exploring the Potential of Metacognitive Support Agents for Human-AI Co-Creation","created":"2025-06-15","cited_by_count":6,"area":null},{"id":"2406.00146","title":"A Survey of Deep Learning Audio Generation Methods","created":"2024-05-31","cited_by_count":5,"area":null},{"id":"2410.19898","title":"A Review of Deep Learning Approaches for Non-Invasive Cognitive Impairment Detection","created":"2024-10-25","cited_by_count":5,"area":null},{"id":"2309.03378","title":"RoDia: A New Dataset for Romanian Dialect Identification from Speech","created":"2023-09-06","cited_by_count":4,"area":null},{"id":"2507.20443","title":"Provable In-Context Learning of Nonlinear Regression with Transformers","created":"2025-07-28","cited_by_count":4,"area":null},{"id":"2401.01537","title":"The Art of Deception: Robust Backdoor Attack using Dynamic Stacking of Triggers","created":"2024-01-03","cited_by_count":3,"area":null},{"id":"2410.13114","title":"Sound Check: Auditing Audio Datasets","created":"2024-10-17","cited_by_count":3,"area":null},{"id":"2410.13342","title":"DART: Disentanglement of Accent and Speaker Representation in Multispeaker Text-to-Speech","created":"2024-10-17","cited_by_count":3,"area":null},{"id":"2507.05885","title":"How to Evaluate Automatic Speech Recognition: Comparing Different Performance and Bias Measures","created":"2025-07-08","cited_by_count":3,"area":null},{"id":"2405.09470","title":"Towards Evaluating the Robustness of Automatic Speech Recognition Systems via Audio Style Transfer","created":"2024-05-15","cited_by_count":2,"area":null},{"id":"2408.09202","title":"A Deep Neural Network Framework for Solving Forward and Inverse Problems in Delay Differential Equations","created":"2024-08-17","cited_by_count":2,"area":null},{"id":"2409.10048","title":"Audio-Driven Reinforcement Learning for Head-Orientation in Naturalistic Environments","created":"2024-09-16","cited_by_count":2,"area":"deeprl"},{"id":"2502.10089","title":"A Hybrid Edge Classifier: Combining TinyML-Optimised CNN with RRAM-CMOS ACAM for Energy-Efficient Inference","created":"2025-02-14","cited_by_count":2,"area":null},{"id":"2502.10822","title":"NeuroAMP: A Novel End-to-end General Purpose Deep Neural Amplifier for Personalized Hearing Aids","created":"2025-02-15","cited_by_count":2,"area":null},{"id":"2504.00858","title":"Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systems","created":"2025-04-01","cited_by_count":2,"area":null},{"id":"2504.19197","title":"Generative Adversarial Network based Voice Conversion: Techniques, Challenges, and Recent Advancements","created":"2025-04-27","cited_by_count":2,"area":null},{"id":"2506.03515","title":"BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2507.00808","title":"Multi-interaction TTS toward professional recording reproduction","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2510.12573","title":"Learning Human Motion with Temporally Conditional Mamba","created":"2025-10-14","cited_by_count":2,"area":"ssm"},{"id":"2305.12301","title":"Sentence Embedder Guided Utterance Encoder (SEGUE) for Spoken Language Understanding","created":"2023-05-20","cited_by_count":1,"area":null},{"id":"2312.00581","title":"Pathway to a fully data-driven geotechnics: lessons from materials informatics","created":"2023-12-01","cited_by_count":1,"area":null},{"id":"2404.04645","title":"HyperTTS: Parameter Efficient Adaptation in Text to Speech using Hypernetworks","created":"2024-04-06","cited_by_count":1,"area":null},{"id":"2405.17376","title":"Federating Dynamic Models using Early-Exit Architectures for Automatic Speech Recognition on Heterogeneous Clients","created":"2024-05-27","cited_by_count":1,"area":"inference"},{"id":"2406.05153","title":"Integrating Physics of the Problem into Data-Driven Methods to Enhance Elastic Full-Waveform Inversion with Uncertainty Quantification","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2406.17257","title":"Leveraging Parameter-Efficient Transfer Learning for Multi-Lingual Text-to-Speech Adaptation","created":"2024-06-25","cited_by_count":1,"area":null},{"id":"2409.04949","title":"Attention-Based Efficient Breath Sound Removal in Studio Audio Recordings","created":"2024-09-08","cited_by_count":1,"area":null},{"id":"2410.09734","title":"Gradient-Free Training of Quantized Neural Networks","created":"2024-10-13","cited_by_count":1,"area":null},{"id":"2410.19586","title":"Diverse Sign Language Translation","created":"2024-10-25","cited_by_count":1,"area":null},{"id":"2510.23252","title":"Are ASR foundation models generalized enough to capture features of regional dialects for low-resource languages?","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2512.09806","title":"CHEM: Estimating and Understanding Hallucinations in Deep Learning for Image Processing","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2604.10202","title":"Wolkowicz-Styan Upper Bound on the Hessian Eigenspectrum for Cross-Entropy Loss in Nonlinear Smooth Neural Networks","created":"2026-04-11","cited_by_count":1,"area":null},{"id":"2306.02568","title":"Latent Optimal Paths by Gumbel Propagation for Variational Bayesian Dynamic Programming","created":"2023-06-05","cited_by_count":0,"area":null},{"id":"2409.07466","title":"An Artificial Neural Network for Image Classification Inspired by Aversive Olfactory Learning Circuits in Caenorhabditis Elegans","created":"2024-08-28","cited_by_count":0,"area":null},{"id":"2410.16345","title":"Exploring how deep learning decodes anomalous diffusion via Grad-CAM","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2504.08964","title":"Bidirectional Linear Recurrent Models for Sequence-Level Multisource Fusion","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2504.20097","title":"Long-Distance Field Demonstration of Imaging-Free Drone Identification in Intracity Environments","created":"2025-04-26","cited_by_count":0,"area":null},{"id":"2505.02369","title":"Sharpness-Aware Minimization with Z-Score Gradient Filtering","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2508.11598","title":"Representing Speech Through Autoregressive Prediction of Cochlear Tokens","created":"2025-08-15","cited_by_count":0,"area":null},{"id":"2509.05679","title":"Distributed Deep Learning using Stochastic Gradient Staleness","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2509.15024","title":"Attention Beyond Neighborhoods: Reviving Transformer for Graph Clustering","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2510.27004","title":"Mixture-of-Transformers Learn Faster: A Theoretical Study on Classification Problems","created":"2025-10-30","cited_by_count":0,"area":"moe"},{"id":"2601.09716","title":"Opportunities and Challenges of Natural Language Processing for Low-Resource Senegalese Languages in Social Science Research","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2605.17860","title":"PAREDA: A Multi-Accent Speech Dataset of Natural Language Processing Research Discussions","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.28662","title":"Closed-Form Steepest Descent Direction toward Flat Minima: Reducing Upper Bounds on the Loss Hessian Eigenspectrum in Neural Networks","created":"2026-06-27","cited_by_count":0,"area":null}],"next_cursor":null}