mbrotos / SoundSeg
Spectral Mapping of Singing Voices: U-Net-Assisted Vocal Segmentation
☆10Updated last month
Related projects: ⓘ
- My hybrid TTS network that combines, VALL-E, VoiceBox, SpeechFlow, Seamless and TortoiseTTS into one☆27Updated last month
- ☆21Updated last year
- ☆26Updated this week
- Speech enhancement in noisy and reverberant environments using deep neural networks☆15Updated last month
- Viterbi decoding in PyTorch☆23Updated 3 weeks ago
- Production-ready vocoder using BigVSAN☆11Updated 7 months ago
- GPT for FACodec☆13Updated 5 months ago
- The source code for the paper CrossSinger (asru2023)☆18Updated 11 months ago
- A robust pitch tracker using synchro-squeezed fft and frequency domain autocorrelation☆34Updated 8 months ago
- Aligner for text-to-speech☆15Updated 2 months ago
- Multispeaker Community Vocoder Model for DiffSinger☆34Updated 4 months ago
- Codebase and project page for EDMSound☆29Updated 10 months ago
- 60k hours of phoneme-aligned audio from audio books☆18Updated last month
- My vocoder experiments☆20Updated last month
- Vocoder-Free Non-Parallel Conversion of Whispered Speech With Masked Cycle-Consistent Generative Adversarial Networks☆17Updated last year
- A neural speech codec based on discrete WavLM representations☆14Updated 3 weeks ago
- ☆21Updated this week
- ☆33Updated 2 months ago
- ☆12Updated last year
- ☆24Updated 2 months ago
- Official repository for NAST: Noise Aware Speech Tokenization for Speech Language Models (Interspeech 2024) https://arxiv.org/abs/2406.11…☆40Updated 2 months ago
- (R&D) Text to speech using phonemes as inputs and audio codec codes as outputs. Loosely based on MegaByte, VALL-E and Encodec.☆46Updated last year
- An implementation of Charactr, Inc's "WavThruVec: Latent speech representation as intermediate features for neural speech synthesis"☆24Updated last year
- Phonemes and durations labeling based on whisper small☆12Updated 2 months ago
- ☆13Updated 2 weeks ago
- ESLTTS dataset☆15Updated 3 months ago
- text to speech☆10Updated 6 months ago
- ☆25Updated last year
- ☆14Updated 4 months ago
- Export an ONNX graph that performs ISTFT. Designed for TTS models.☆18Updated 4 months ago