nii-yamagishilab/project-NN-Pytorch-scripts

see README

What it solves

This repository provides a collection of tools and scripts for speech processing, specifically focusing on neural waveform models (vocoders) and speech spoofing countermeasures (anti-spoofing) to detect synthetic or manipulated audio.

How it works

The project is organized as a library of PyTorch-based implementations. It includes core scripts for training and data I/O, finalized PyTorch modules, and specific project directories. Each project typically contains a main.py for execution, a model.py for the architecture, and a config.py for dataset settings.

Who it’s for

It is designed for researchers and developers working in speech synthesis, audio forensics, and speech security, as well as those learning how to implement neural vocoders and anti-spoofing systems.

Highlights

  • Speech Spoofing Countermeasures: Multiple implementations focusing on confidence estimation, self-supervised learning (SSL) feature extractors, and active learning frameworks.
  • Neural Vocoders: Implementations of various waveform models including WaveNet, WaveGlow, iLPCNet, and Neural Source-Filter (NSF) models.
  • Educational Resources: Includes tutorials on neural vocoders, anti-spoofing, and voice privacy challenges.
  • Research-Backed: Contains code and resources associated with several ICASSP and SLT publications.

Related

  • Project
    kaanozhan/Frame

    Frame is an Electron‑based IDE that gives AI coding agents a persistent, git‑anchored context. It creates a standard `.frame/` folder with rules, a module map, notes, tasks and markdown‑based specs (spec/plan/tasks/outcome). Agents start each session with this context, and a built‑in conductor can run multiple specs in parallel isolated git worktrees, enforcing non‑overlapping footprints and requiring human approval before merging. Features include a multi‑terminal grid, task/spec panels, GitHub integration, fast intent‑index lookup, and support for Claude Code, Codex CLI, and Gemini CLI. Installation is via `npm install` or pre‑built binaries; the project is Apache‑2.0 licensed.

  • Project
    ntd4996/agentpet

    AgentPet is a cross‑platform desktop app that monitors the live state of AI coding agents and gamifies the experience with a tamagotchi‑style pet that levels up based on token usage and completed sessions. It works offline, supports many agents, offers per‑project dashboards, and provides optional web sync and leaderboards.

  • Project
    AThevon/genjutsu

    genjutsu is a Claude‑AI plugin that lets you ask an LLM to add or redesign motion‑heavy UI elements. Two main skills – `/genjutsu:cast` for small, targeted animations and `/genjutsu:paint` for full‑scale redesigns – automatically detect your stack (React/Vue/Svelte, Compose, SwiftUI), propose an interaction thesis, generate the code (GSAP, Framer Motion, Compose, SwiftUI, etc.), and run a quick audit for accessibility and performance. Install via a single ZIP bundle or individual skill ZIPs on Claude AI, Claude Code, or Cowork.

  • Project
    kigner/audio.cpp-webui

    A high-performance C++ audio inference framework based on ggml that enables fast, portable local execution of TTS, ASR, and voice cloning models across multiple hardware backends.