Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Model
cs.SD, cs.AI, cs.CL, cs.LG, eess.AS
Submitted: 2026-10-05
Updated: 2026-10-05
Code: https://github.com/sahilmahendrakar/paradee
Sources
- Neural Speech Phase Prediction based on Parallel Estimation Architecture and Anti-Wrapping Losses
- APNet: An All-Frame-Level Neural Vocoder Incorporating Direct Prediction of Amplitude and Phase Spectra
- The Limits of Reference-Free Speech Quality Metrics as Evaluators and Rewards on Modern Text-to-Speech
- The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech
- WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
- Nix-TTS: Lightweight and End-to-End Text-to-Speech via Module-wise Distillation
- High Fidelity Neural Audio Compression
- APNet2: High-quality and High-efficiency Neural Vocoder with Direct Prediction of Amplitude and Phase Spectra
- A Distilled Low-Latency Neural Vocoder with Explicit Amplitude and Phase Prediction
- Distilling the Knowledge in a Neural Network
- Attacking UTMOS: Probing the Robustness of a Speech Quality Assessment Model
- Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization
- UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation
- iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform
- iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNN
- Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform
- SupertonicTTS: Towards Highly Efficient and Streamlined Text-to-Speech System
- Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
- HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
- High-Fidelity Audio Compression with Improved RVQGAN
Related papers
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems
- AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
- SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving
- WASIL: In-the-Wild Arabic Spoken Interactions with LLMs