{"total":30,"rows":[{"id":"2410.07168","title":"Sylber: Syllabic Embedding Representation of Speech from Raw Audio","created":"2024-10-09","cited_by_count":19,"area":null},{"id":"2406.12998","title":"Coding Speech through Vocal Tract Kinematics","created":"2024-06-18","cited_by_count":18,"area":null},{"id":"2310.10788","title":"Self-Supervised Models of Speech Infer Universal Articulatory Kinematics","created":"2023-10-16","cited_by_count":16,"area":null},{"id":"2602.18899","title":"[b] = [d] - [t] + [p]: Self-supervised Speech Models Discover Phonological Vector Arithmetic","created":"2026-02-21","cited_by_count":12,"area":null},{"id":"2407.18517","title":"SLIM: Style-Linguistics Mismatch Model for Generalized Audio Deepfake Detection","created":"2024-07-26","cited_by_count":8,"area":null},{"id":"2603.12642","title":"Self-Supervised Speech Models Encode Phonetic Context via Position-dependent Orthogonal Subspaces","created":"2026-03-13","cited_by_count":8,"area":null},{"id":"2309.09220","title":"Improving Speech Inversion Through Self-Supervised Embeddings and Enhanced Tract Variables","created":"2023-09-17","cited_by_count":7,"area":null},{"id":"2410.07379","title":"Learn from Real: Reality Defender's Submission to ASVspoof5 Challenge","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2308.06443","title":"Neural Latent Aligner: Cross-trial Alignment for Learning Representations of Complex, Naturalistic Neural Data","created":"2023-08-12","cited_by_count":5,"area":null},{"id":"2403.20184","title":"Exploring Pathological Speech Quality Assessment with ASR-Powered Wav2Vec2 in Data-Scarce Context","created":"2024-03-29","cited_by_count":5,"area":null},{"id":"2506.10289","title":"RT-VC: Real-Time Zero-Shot Voice Conversion with Speech Articulatory Coding","created":"2025-06-12","cited_by_count":4,"area":null},{"id":"2406.15754","title":"Multimodal Segmentation for Vocal Tract Modeling","created":"2024-06-22","cited_by_count":3,"area":null},{"id":"2409.02451","title":"Fast, High-Quality and Parameter-Efficient Articulatory Synthesis using Differentiable DSP","created":"2024-09-04","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":"2510.23969","title":"emg2speech: Synthesizing speech from electromyography using self-supervised speech models","created":"2025-10-28","cited_by_count":3,"area":null},{"id":"2406.18731","title":"WavRx: a Disease-Agnostic, Generalizable, and Privacy-Preserving Speech Health Diagnostic Model","created":"2024-06-26","cited_by_count":2,"area":null},{"id":"2509.00503","title":"Entropy-based Coarse and Compressed Semantic Speech Representation Learning","created":"2025-08-30","cited_by_count":2,"area":null},{"id":"2601.22306","title":"Sylber 2.0: A Universal Syllable Embedding","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2604.10123","title":"Training-Free Cross-Lingual Dysarthria Severity Assessment via Phonological Subspace Analysis in Self-Supervised Speech Representations","created":"2026-04-11","cited_by_count":2,"area":null},{"id":"2505.20529","title":"Training Articulatory Inversion Models for Interspeaker Consistency","created":"2025-05-26","cited_by_count":1,"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":"2604.18920","title":"Comparison of sEMG Encoding Accuracy Across Speech Modes Using Articulatory and Phoneme Features","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2408.04363","title":"Simulating Articulatory Trajectories with Phonological Feature Interpolation","created":"2024-08-08","cited_by_count":0,"area":null},{"id":"2501.16201","title":"Enhancing and Exploring Mild Cognitive Impairment Detection with W2V-BERT-2.0","created":"2025-01-27","cited_by_count":0,"area":null},{"id":"2506.08981","title":"FROST-EMA: Finnish and Russian Oral Speech Dataset of Electromagnetic Articulography Measurements with L1, L2 and Imitated L2 Accents","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2511.07955","title":"Speech Emotion Recognition with Phonation Excitation Information and Articulatory Kinematics","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2604.21706","title":"Phonological Subspace Collapse Is Aetiology-Specific and Cross-Lingually Stable: Evidence from 3,374 Speakers","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2606.22020","title":"What Do Neural Networks Learn for TDOA Estimation? A Cross-Architecture Probing Study","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2608.15411","title":"A survey of AI-generated voices and their detection","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2610.16273","title":"Deep Speech Representations Track Word Timing along a Low-Dimensional Circular Trajectory","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}