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.
AudioCodec-Hub is a Python library for encoding and decoding audio data, supporting various neural audio codec models
Official inference code and checkpoints for CodecSlime.
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.
Reproducible benchmark for neural audio codecs on phone-degraded speech: SNAC vs EnCodec round-trips on FLEURS + noisekit (clean, telecom, noisy). STOI, narrowband PESQ @ 8 kHz, SNR, GPU latency. Colab notebook and baseline results.
Official PyTorch implementation of GS-Codec: A Gaussian-Splatting Bottleneck for Neural Audio Coding (NeurIPS 2026)
To associate your repository with the speech-codec topic, visit your repo's landing page and select "manage topics."