Similares a TRAMBA: A Hybrid Transformer and Mamba Architecture for Practical Audio and Bone Conduction Speech

20 vecinos (text_768) · 50 views · ACM SIGCHI · Estados Unidos


★	TRAMBA: A Hybrid Transformer and Mamba Architecture for Practical Audio and Bone Conduction Speech	ACM SIGCHI @sigchi	50	Estados Unidos
5	OpenEarable 2.0: Open-Source Earphone Platform for Physiological Ear Sensing	ACM SIGCHI @sigchi	1.2K	Estados Unidos	88
8	Impact of Time Discrepancies on Machine Learning Performance for Multi-Wearable HAR	ACM SIGCHI @sigchi	402	Estados Unidos	88
9	From Neck to Head: Bio-Impedance Sensing for Head Pose Estimation	ACM SIGCHI @sigchi	174	Estados Unidos	88
2	An Efficient and High-speed sEMG-based Transient-state Micro-gesture Recognition Method on Wearables	ACM SIGCHI @sigchi	169	Estados Unidos	88
10	Closed-Loop Rhythmic Haptic Biofeedback via Smartwatch for Relaxation and Sleep Onset	ACM SIGCHI @sigchi	167	Estados Unidos	88
11	Ring-a-Pose: A Ring for Continuous Hand Pose Tracking	ACM SIGCHI @sigchi	145	Estados Unidos	88
15	Beyond Symbols: Motion Perception Cues Enhance Dual-Task Performance w Wearable Directional Guidance	ACM SIGCHI @sigchi	129	Estados Unidos	87
16	Temporal Action Localization for Inertial-based Human Activity Recognition	ACM SIGCHI @sigchi	107	Estados Unidos	87
7	W2W: A Simulated Exploration of IMU Placement Across the Human Body for Designing Smarter Wearable	ACM SIGCHI @sigchi	98	Estados Unidos	88
3	TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient HAR on Edge Devices	ACM SIGCHI @sigchi	76	Estados Unidos	88
4	Step-Aware Voice Assistant on a Smartwatch Enabled by Multimodal Procedure Tracking and LLMs	ACM SIGCHI @sigchi	68	Estados Unidos	88
20	GLOSS: Group of LLMs for Open-ended Sensemaking of Passive Sensing Data for Health and Wellbeing	ACM SIGCHI @sigchi	68	Estados Unidos	87
19	Respiration Rate Estimation via Smartwatch-based Photoplethysmography and Accelerometer Data	ACM SIGCHI @sigchi	62	Estados Unidos	87
12	Tecnología asistencial para personas con discapacidad	Atomun teleSUR @atomuntelesur	60	Venezuela	88
14	CRoP: Context-wise Robust Static Human-Sensing Personalization	ACM SIGCHI @sigchi	58	Estados Unidos	87
17	The Manipulative Power of Voice Characteristics	ACM SIGCHI @sigchi	55	Estados Unidos	87
1	USpeech: Ultrasound-Enhanced Speech with Minimal Human Effort via Cross-Modal Synthesis	ACM SIGCHI @sigchi	37	Estados Unidos	91
6	¡Audio PERFECTO con IA! Nueva Tecnología Hydra Mejora el Sonido	AudioArXiv @audioarxiv	34	—	88
18	Energy Efficient On Chip Adaptive Spike Sorting And Multiresolution DWT Via Reconfigurable MAC And C	Computer Science & IT Conference Proceedings @computerscienceitconferenc7375	30	Australia	87
13	Multimodal Transformers Explained: Unifying All Data Types	THE FACT FACTORY @thefactfactoryf	14	—	87