entn-at / DurIAN-1
Implementation of "DurIAN: Duration Informed Attention Network For Multimodal Synthesis".
☆14Updated 4 years ago
Related projects: ⓘ
- Transfer Learning from Monolingual ASR to Transcription-free Cross-lingual Voice Conversion☆39Updated last year
- ☆45Updated 4 years ago
- TTS Text Analyzer☆31Updated last year
- PPSpeech: Phrase based Parallel End-to-End TTS System☆35Updated 4 years ago
- Voice conversion model for real-time speech synthesis using PPG (Phonetic PosteriorGram) as an intermediate feature, written in Pytorch.☆26Updated 2 years ago
- TPSE-GST Tacotron2☆14Updated 5 years ago
- The Official Implementation of “Content-Dependent Fine-Grained Speaker Embedding for Zero-Shot Speaker Adaptation in Text-to-Speech Synth…☆81Updated last year
- Simulation of parallel synthesis with LPCNet vocoder☆14Updated 4 years ago
- Pytorch implementation of LearnableUpsamplingLayer (NaturalSpeech, Tan et al., 2022)☆54Updated 6 months ago
- This repository provides UNOFFICIAL Bunched LPCNet implementations with Pytorch.☆14Updated 3 years ago
- new version of tacotron2 (old version: https://github.com/xcmyz/Tacotron2-Pytorch)☆8Updated 3 years ago
- Materials accompanying the paper "Phonological features for 0-shot multilingual speech synthesis"☆31Updated 4 years ago
- This repo contains conv-tasnet for basis-melgan. If you want to get code of basis-melgan, please refer to FastVocoder.☆19Updated 3 years ago
- ☆67Updated 3 years ago
- ☆17Updated this week
- E2E TTS using Conditional Flow Matching (Experimental*)☆65Updated 10 months ago
- ☆23Updated this week
- Unofficial pytorch reproduction for the paper "Utilizing Neural Transducers for Two-Stage Text-to-Speech via Semantic Token Prediction" (…☆58Updated 5 months ago
- An imporved version of Fastsinging singing voice synthesising system.☆20Updated 3 years ago
- Official implementation of FCL-taco2: Fast, Controllable and Lightweight version of Tacotron2 @ ICASSP 2021☆39Updated 3 years ago
- PyTorch implementation of Tacotron and Tacotron2☆32Updated 2 years ago
- Objective metrics used in several text-to-speech (TTS) papers.☆46Updated 2 years ago
- ERISHA is a mulitilingual multispeaker expressive speech synthesis framework. It can transfer the expressivity to the speaker's voice for…☆43Updated 3 years ago
- with alignment learning and continuous wavelet transform☆19Updated 2 years ago
- Google's TPGST reimplementation.☆34Updated 4 years ago
- ☆28Updated this week
- Singing Voice Speech modeling test☆35Updated 2 years ago
- Ultrafast GAN based Vocoder for Text to Speech☆50Updated 2 years ago
- A toy-like Text-to-Speech for Chinese/Mandarin synthesize, inspired by Tacotron & FastSpeech2 & RefineGAN.☆15Updated 2 years ago
- RepVgg + HiFiGAN☆33Updated 2 years ago