aiqbench analysis
MyoCodec introduces a streaming neural codec for electromyography (EMG) signals that bridges the gap between biosignal processing and modern token-based AI architectures. By combining causal Transformers with residual vector quantization, it enables efficient real-time encoding into discrete tokens suitable for downstream tasks like typing, gesture recognition, and speech synthesis. This work demonstrates how specialized neural codecs can facilitate direct integration of physiological data into large language model ecosystems.
MyoCodec: A Streaming Neural Codec for Electromyography
arXiv:2609.36687v1 Announce Type: cross Abstract: Neural codecs encode continuous signals into compact sequences of discrete tokens, providing an interface for efficient transmission, storage, and token-based sequence modeling. This paradigm has been widely adopted in modern speech and audio frameworks; however, the biosignal domain still lacks a neural codec designed specifically for low-bitrate streaming and generalization across diverse downstream tasks. We present MyoCodec, a streaming neural codec designed for electromyography (EMG). Inspired by recent neural audio codecs, MyoCodec combines causal Transformers with residual vector quantization to encode continuous EMG signals into different levels of EMG representations spanning from continuous latent features to discrete tokens operating at 50 Hz. Trained on twelve public EMG datasets, MyoCodec achieves favorable performance in both intrinsic codec quality and representative downstream tasks, including typing (emg2qwerty), hand-pose (emg2pose), speech decoding (emg2speech), and speech-to-EMG synthesis (speech2emg). Across these tasks, MyoCodec exhibits strong performance against prior models while providing a compact and causal EMG representation. During streaming inference, it requires compute time of only 0.482 ms for each 20 ms frame, enabling real-time streaming. Also, the discrete token representation provided by MyoCodec has the potential to support integration into language-model based approaches, creating a path toward LLM-based interactive systems, where tokenized EMG representations are directly processed into such language or speech models. Code and model weights are released.
Abstract:Neural codecs encode continuous signals into compact sequences of discrete tokens, providing an interface for efficient transmission, storage, and token-based sequence modeling. This paradigm has been widely adopted in modern speech and audio frameworks; however, the biosignal domain still lacks a neural codec designed specifically for low-bitrate streaming and generalization across diverse downstream tasks. We present MyoCodec, a streaming neural codec designed for electromyography (EMG). Inspired by recent neural audio codecs, MyoCodec combines causal Transformers with residual vector quantization to encode continuous EMG signals into different levels of EMG representations spanning from continuous latent features to discrete tokens operating at 50 Hz. Trained on twelve public EMG datasets, MyoCodec achieves favorable performance in both intrinsic codec quality and representative downstream tasks, including typing (emg2qwerty), hand-pose (emg2pose), speech decoding (emg2speech), and speech-to-EMG synthesis (speech2emg). Across these tasks, MyoCodec exhibits strong performance against prior models while providing a compact and causal EMG representation. During streaming inference, it requires compute time of only 0.482 ms for each 20 ms frame, enabling real-time streaming. Also, the discrete token representation provided by MyoCodec has the potential to support integration into language-model based approaches, creating a path toward LLM-based interactive systems, where tokenized EMG representations are directly processed into such language or speech models. Code and model weights are released.
Signal Processing (eess.SP); Artificial Intelligence (cs.AI)
arXiv:2609.36687 [eess.SP]
(or arXiv:2609.36687v1 [eess.SP] for this version)
https://doi.org/10.48550/arXiv.2609.36687 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 311 words
Related coverage
LILAC: An Idempotent Neural Speech Codec
arXiv · Aug 7, 2026
ZipCodec: Ultra-Low-Frame-Rate Streaming Speech Coding
arXiv · Sep 12, 2026
HybridCodec: Fast Dual-Stream, Semantically Enhanced Neural Audio Codec
arXiv · Jun 8, 2026
Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec
arXiv · Sep 2, 2026