Ultra-low bitrate speech codec (0.27-1 kbps) with cross-modal alignment and real-time capabilities
Ultra-low-bitrate Speech Codec for Speech Language Modeling Applications
ICASSP 2024 - Generative De-Quantization for Neural Speech Codec via Latent Diffusion.
microphone array speech generator (MASG) in room acoustic
AudioCodec-Hub is a Python library for encoding and decoding audio data, supporting various neural audio codec models
3GPP Codec for Enhanced Voice Services (EVS)
Official inference code and checkpoints for CodecSlime.
Official repo of ICASSP 2021 paper Source-Aware Neural Speech Coding for Noisy Speech Compression (SANAC)
Pure-Rust Opus audio codec (RFC 6716) with Ogg encapsulation (RFC 7845). Encoder and decoder for SILK, CELT and hybrid modes. No C, no FFI, no dependencies.
Hide digital data inside speech-shaped audio that survives Zoom, Discord, WhatsApp, and cellular voice. Reproducible Pareto curve of six trained codecs spanning 76 bps (cellular) to 3196 bps (Zoom-class) with listenable demos.
test scripts for test lyra voice codec
Experimental Lyra V2 speech codec for WebGPU/WGSL with a browser recording demo at 3.2, 6, and 9.2 kbps.
A few seconds of speech inside an ordinary QR code. Open format, CVQR1: payloads, decoded entirely offline.
Experimental 1–2.4 kbps Lyra V2 WebGPU modes, with microphone recording and prerecorded speech comparisons. Quality unqualified.
To associate your repository with the speech-codec topic, visit your repo's landing page and select "manage topics."