{"total":19,"rows":[{"id":"2311.18188","title":"Speech Understanding on Tiny Devices with A Learning Cache","created":"2023-11-30","cited_by_count":3,"area":null},{"id":"2406.15754","title":"Multimodal Segmentation for Vocal Tract Modeling","created":"2024-06-22","cited_by_count":3,"area":null},{"id":"2505.24059","title":"Towards disentangling the contributions of articulation and acoustics in multimodal phoneme recognition","created":"2025-05-29","cited_by_count":3,"area":null},{"id":"2411.07619","title":"Artificial Intelligence for Biomedical Video Generation","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2503.12102","title":"A Speech-to-Video Synthesis Approach Using Spatio-Temporal Diffusion for Vocal Tract MRI","created":"2025-03-15","cited_by_count":2,"area":null},{"id":"2506.01119","title":"MOOSE: Pay Attention to Temporal Dynamics for Video Understanding via Optical Flows","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2509.13767","title":"VocSegMRI: Multimodal Learning for Precise Vocal Tract Segmentation in Real-time MRI","created":"2025-09-17","cited_by_count":2,"area":null},{"id":"2603.04840","title":"An Approach to Simultaneous Acquisition of Real-Time MRI Video, EEG, and Surface EMG for Articulatory, Brain, and Muscle Activity During Speech Production","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2509.21447","title":"ARTI-6: Towards Six-dimensional Articulatory Speech Encoding","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2603.10371","title":"Speech Codec Probing from Semantic and Phonetic Perspectives","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2605.18221","title":"SIREM: Speech-Informed MRI Reconstruction with Learned Sampling","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2402.16908","title":"Lightweight, error-tolerant edge detection using memristor-enabled stochastic logics","created":"2024-02-25","cited_by_count":0,"area":null},{"id":"2501.06229","title":"Open-Source Manually Annotated Vocal Tract Database for Automatic Segmentation from 3D MRI Using Deep Learning: Benchmarking 2D and 3D Convolutional and Transformer Networks","created":"2025-01-08","cited_by_count":0,"area":null},{"id":"2502.14418","title":"Role of the Pretraining and the Adaptation data sizes for low-resource real-time MRI video segmentation","created":"2025-02-20","cited_by_count":0,"area":null},{"id":"2503.06588","title":"Speech Audio Generation from dynamic MRI via a Knowledge Enhanced Conditional Variational Autoencoder","created":"2025-03-09","cited_by_count":0,"area":null},{"id":"2505.05647","title":"A New k-Space Model for Non-Cartesian Fourier Imaging","created":"2025-05-08","cited_by_count":0,"area":null},{"id":"2608.09767","title":"Structured Phonological Representations for Audio-Articulatory rtMRI Speech Classification","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.09757","title":"Arti-JEPA: Adapting Video World Model to Real-Time MRI of the Vocal Tract for Speech-Production Analysis","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.36737","title":"Reconstructing the Vocal Tract with Differentiable Acoustic Simulation","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}