mlsanityData to 7 Oct 2026

An Improved Model for Voicing Silent Speech

arXiv 2106.01933 ↗First posted 3 Jun 2021eess.AS cs.CL cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

In this paper, we present an improved model for voicing silent speech, where audio is synthesized from facial electromyography (EMG) signals. To give our model greater flexibility to learn its own input features, we directly use EMG signals as input in the place of hand-designed features used by prior work. Our model uses convolutional layers to extract features from the signals and Transformer layers to propagate information across longer distances. To provide better signal for learning, we also introduce an auxiliary task of predicting phoneme labels in addition to predicting speech audio features. On an open vocabulary intelligibility evaluation, our model improves the state of the art for this task by an absolute 25.8%.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 7 of its 21 references that are in the map. First posted on arXiv 3 Jun 2021.

Builds on

7 of 21 references.

References · 7

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  4. 2018Self-Attention with Relative Position Representationscited by 1,112
  5. 2014Deep Speech: Scaling up end-to-end speech recognitioncited by 354
  6. 2016Wav2Letter: an End-to-End ConvNet-based Speech Recognition Systemcited by 43
  7. 2020Digital Voicing of Silent Speechcited by 24

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 7; 2026: 4.

15 papers.

Sort:

By area:

  1. 2024A Cross-Modal Approach to Silent Speech with LLM-Enhanced Recognitioncited by 9
  2. 2025Can LLMs Understand Unvoiced Speech? Exploring EMG-to-Text Conversion with LLMscited by 6
  3. 2025TinyMyo: a Tiny Foundation Model for Flexible EMG Signal Processing at the Edgecited by 5
  4. 2024Diff-ETS: Learning a Diffusion Probabilistic Model for Electromyography-to-Speech Conversioncited by 4
  5. 2025Articulatory Feature Prediction from Surface EMG during Speech Productioncited by 4
  6. 2024Multimodal Segmentation for Vocal Tract Modelingcited by 3
  7. 2025emg2speech: Synthesizing speech from electromyography using self-supervised speech modelscited by 3
  8. 2024Geometry of orofacial neuromuscular signals: speech articulation decoding using surface electromyographycited by 1
  9. 2025A Silent Speech Decoding System from EEG and EMG with Heterogenous Electrode Configurationscited by 0
  10. 2025CIS-BWE: Chaos-Informed Speech Bandwidth Extensioncited by 0
  11. 2025Reconstructing Unseen Sentences from Speech-related Biosignals for Open-vocabulary Neural Communicationcited by 0
  12. 2026SoniSpeech: A Large-Scale Open-Vocabulary Tri-Modal Dataset for Wearable Silent Speech Interfacescited by 0
3 more
  1. 2026Myovox: Reading Speech from the Muscles of the Facecited by 0
  2. 2026Multi-Subject Pretraining Enables Short-Calibration Personalization for Closed-Corpus Surface EMG Speech Decodingcited by 0
  3. 2026MyoCodec: A Streaming Neural Codec for Electromyographycited by 0