mlsanityData to 14 Oct 2026

SoniSpeech: A Large-Scale Open-Vocabulary Tri-Modal Dataset for Wearable Silent Speech Interfaces

arXiv 2608.00803 ↗First posted 1 Aug 2026cs.SD cs.HC cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Wearable silent speech interfaces (SSIs) are limited to small, closed vocabularies. Approaches achieving larger vocabularies require obtrusive hardware such as facial electrodes. We present SoniSpeech, the first large-scale, open-vocabulary, trimodal dataset for wearable SSI using acoustic-sensing eyewear. It contains 34 hours across 18,000 utterances with three synchronized modalities: ultrasound echo profiles, voiced audio, and frontal video, in both voiced and silent modes. The corpus draws from the SODA dialogue dataset, providing contemporary conversational English with 5,356 unique words and full phoneme coverage. A CTC-based ResNet-34 baseline achieves 26.3% word error rate (WER) on open-vocabulary silent speech recognition, the first benchmark for this task. Dataset is available at https://doi.org/10.7298/xjjr-9m85

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 36 references that are in the map. First posted on arXiv 1 Aug 2026.

Builds on

18 of 36 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  3. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
  4. 2022SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualizationcited by 168
  5. 2020Digital Voicing of Silent Speechcited by 24
  6. 2021An Improved Model for Voicing Silent Speechcited by 15
  7. 2024Scaling Law in Neural Data: Non-Invasive Speech Decoding with 175 Hours of EEG Datacited by 13
  8. 2020TaL: a synchronised multi-speaker corpus of ultrasound tongue imaging, audio, and lip videoscited by 12
  9. 2024A Cross-Modal Approach to Silent Speech with LLM-Enhanced Recognitioncited by 9
  10. 2024EchoWrist: Continuous Hand Pose Tracking and Hand-Object Interaction Recognition Using Low-Power Active Acoustic Sensing On a Wristbandcited by 8
  11. 2024Ring-a-Pose: A Ring for Continuous Hand Pose Trackingcited by 3
  12. 2024ActSonic: Recognizing Everyday Activities from Inaudible Acoustic Wave Around the Bodycited by 3
6 more
  1. 2026WatchHand: Enabling Continuous Hand Pose Tracking On Off-the-Shelf Smartwatchescited by 3
  2. 2024EyeEcho: Continuous and Low-power Facial Expression Tracking on Glassescited by 2
  3. 2025SpellRing: Recognizing Continuous Fingerspelling in American Sign Language using a Ringcited by 2
  4. 2024MunchSonic: Tracking Fine-grained Dietary Actions through Active Acoustic Sensing on Eyeglassescited by 1
  5. 2024SonicID: User Identification on Smart Glasses with Acoustic Sensingcited by 1
  6. 2025EchoForce: Continuous Grip Force Estimation from Skin Deformation Using Active Acoustic Sensing on a Wristbandcited by 1

Built on by

Not cited yet.