# SETU-EMG | Research | Setu Labs Source: https://setu-labs.co/research-emg.html > SETU-EMG: decoding deliberately mouthed silent speech from surface electromyography. A Setu Labs technical summary. Technical summary EMG # Silent speech, from muscle to text. SETU-EMG decodes deliberately mouthed silent speech directly from surface electromyography, sentence by sentence, with no audio at inference time. **Setu Labs**Research · EMG SETU-EMG · Technical summary **16.16%**Word error rate Test partition, 4-gram beam search **10.91%**Character error rate Same decode **35.60%**Word error rate Greedy CTC, no language model **2.14 s**Median latency On an H100; 95th percentile 9.61 s 8 sEMG channels · 1,000 Hz · 63,817,766 parameters · EMG-only at inference ### System SETU-EMG is an end-to-end neural system for decoding deliberately mouthed silent speech directly from surface electromyography (sEMG), enabling sentence-level text decoding without acoustic input at inference time. The system operates on eight channels of articulatory muscle activity sampled at 1,000 Hz and learns a direct mapping from multichannel physiological signals to character sequences. The neural network comprises 63,817,766 trainable parameters and was trained for 200 epochs on a single NVIDIA H100 GPU, with model selection based on silent-speech validation word error rate (WER). ### Training To preserve phonetic information across modalities, training combines silent and voiced EMG with speech audio. Cross-modal representation learning and latent dynamic time warping establish temporal correspondence between EMG and acoustic latent sequences despite timing differences, while connectionist temporal classification (CTC) provides sequence-level supervision for character recognition without requiring manually aligned EMG-to-character labels. ### Inference and results At inference time, the recognition pathway is strictly EMG-only. The model receives processed electrophysiological waveforms and has no access to synchronized audio, reference transcripts, target phoneme sequences, filenames, or reference-dependent metadata. Input signals pass through a deterministic preprocessing pipeline consisting of filtering, resampling, temporal framing, cropping, and amplitude transformation before neural inference. The resulting character probabilities can be decoded directly via greedy CTC or combined with a fixed statistical language model through beam search. On the official held-out test partition of the public silent-speech benchmark (comprising 8 facial EMG channel data of 50+ hours across people), 4-gram beam-search decoding with a beam width of 5,000 achieves a 16.16% WER and a 10.91% character error rate (CER), reducing total word errors from 586 to 266 and increasing exact-transcript matches from 7 to 17 out of 99 utterances, while greedy CTC decoding produces 35.60% WER and 14.35% CER on the same test partition. ### Controls This primary result was obtained from a single neural checkpoint without model ensembling, generative text correction, reference-conditioned reranking, confidence-based rejection, manual editing, or sample exclusion; all test utterances received predictions. A separate validation experiment examined whether higher-level linguistic inference could recover additional information from the model's decoding distribution: ten candidate transcriptions were generated for each of 100 validation utterances (1,939 reference words), after which a frozen language model selected among the candidates without reference transcript access, reducing validation WER from 20.42% to 17.77% and increasing exact matches from 11 to 16. Implementation-level sanity checks were conducted using controlled non-speech inputs: ten zero-valued inputs produced no non-empty outputs, and one out of ten amplitude-matched noise waveforms produced a non-empty transcription. ### Latency and evaluation note Runtime profiling of neural inference followed by greedy and beam-search decoding on an H100 produced a median latency of 2.14 seconds and a 95th-percentile latency of 9.61 seconds. The official benchmark test partition was encountered during broader development and is reported as a fixed benchmark evaluation rather than a previously inaccessible cohort; all model selection and training decisions remained grounded in the designated training and validation partitions. ### Personalization Separately from the benchmark system, SETU-EMG includes an experimental user-personalization capability built around a lightweight 24,576-parameter residual feature adapter while keeping the underlying MONA-derived backbone frozen. The calibration workflow supports training the adapter from labelled, compatible eight-channel recordings, saving and reloading personalized checkpoints, running EMG-only inference with the adapted model, and reverting to the unadapted base model without retraining the backbone. This personalization module was not used to obtain the reported 16.16% test WER. Its software workflow has been implemented and validated, while quantitative improvements for previously unseen users, alternative electrode placements, and the proposed near-ear wearable configuration remain to be demonstrated experimentally. ### Next The next stage extends this decoding framework to proprietary wearable recordings collected across multiple users, sessions, and controlled sensor placements to enable direct measurement of cross-user adaptation, calibration requirements, longitudinal stability, physiological false activations, channel-count sensitivity, and robustness to electrode displacement. These are internal results and have not been peer reviewed. [Next: EEG research →](https://setu-labs.co/research-eeg.html)