Neural Audio Codec: What Determines the Rate–Distortion Ceiling of Scalar-Quantized Speech Codecs?

deep-learning transformers pytorch audio-processing vector-quantization speech-compression neural-audio-codec

• Updated Sep 9, 2026
• Python

A fractal coding framework for audio data

java gpu speech-processing fractals jcuda speech-enhancement fractal-codes fractal-compression speech-compression

• Updated Jun 20, 2017
• Java

Speech reconstruction and compression with autoencoders

deep-learning speech pytorch autoencoders speech-reconstruction speech-compression

• Updated Feb 22, 2022
• Python

Mini SoundStream-style neural audio codec trained on LibriSpeech: 4-codebook RVQ, 3 bitrates, ONNX export

pytorch audio-codec mps vector-quantization librispeech onnx speech-compression apple-silicon residual-vector-quantization neural-codec

• Updated Jun 12, 2026
• Python

iTantra (ISRO SIH26173) — 24 bps neural semantic speech transceiver (React, FastAPI, WebRTC, Faster-Whisper)

react javascript web frontend webrtc whisper sih isro speech-compression fastapi

• Updated Nov 11, 2026
• JavaScript

iTantra (ISRO SIH26173) — Offline Android P2P transceiver with 24 bps neural semantic speech compression & Indic TTS

android kotlin app mobile offline-first p2p tts sih isro speech-compression

• Updated Nov 11, 2026
• Kotlin

A neural codec for speech compression using contextual features and adversarial training. This project implements a high-quality, low-latency speech compression system based on cognitive speech processing principles. Paper: Cognitive Speech Compression with Dual-Context Features Features

generative-adversarial-network speech-compression

• Updated Dec 1, 2025
• Python

Browser voice-QR and push-to-talk app using neural speech compression, WebAssembly, local model caching, and a real-time edge relay.

react typescript webassembly qr-code web-audio cloudflare-workers speech-compression neural-audio-codec

• Updated Oct 19, 2026
• TypeScript