AI & ML
Synthesizing Ultrasonic Echo Profiles from Text for Open-Vocabulary Silent Speech Recognition
arXiv cs.SD0 views
arXiv:2610.15671v1 Announce Type: new Abstract: Eyewear that senses articulation with inaudible ultrasound can now recognize silent speech over an open vocabulary, but its accuracy is limited by the cost of training data. We present SoniGAN, which synthesizes the ultrasonic echo profiles of silent articulation from text and uses them as synthetic supervision. A voice-cloned text-to-speech (TTS) model reads a text corpus, and a two-stage generator synthesizes echo profiles from representations of the spoken content of that audio. Pretraining a recognizer on 104 hours of the synthesized data improves the word error rate (WER) of a public open-vocabulary benchmark by 2.3 points. Adding the sessions the corpus discards for a faulty microphone brings the system to 22.2% without any language model. Lexicon-constrained decoding, LLM rescoring, and ensembling further bring it to 14.9%, the first minimally obtrusive silent speech interface to fall inside the error range in which users report no loss of willingness to use silent speech input.
Source：https://arxiv.org/abs/2610.15671PreviousAnyEdit: A Unified Framework for Speech and Singing Voice Editing with Real-World Environmental ConsistencyNextFlowGRPO for Vocal Separation: From Reward Analysis to Reward Design
Related posts
Sharp Non-Asymptotic Analysis of the Penalized Challenger in $\beta$-EB-TCI for Bernoulli Bandits
0arXiv stat.ML
Toward Optimal Switching Regret for Multi-Armed Bandits with Oblivious Adversary
0arXiv stat.ML
Spectral Condition for $\mu$P under Width-Depth Scaling
0arXiv stat.ML
A Function-Space Stability Boundary for Generalization in Interpolating Learning Systems
0arXiv stat.ML
Who Gets Watched? Allocating Scarce Escalation Resources on Pediatric Wards with Neural Index Policies
0arXiv stat.ML
Minimax Alternating Regret for the Experts Problem and Online Convex Optimization
0arXiv stat.ML