keonlee9420/Stepwise_Monotonic_Multihead_Attention

PyTorch Implementation of Stepwise Monotonic Multihead Attention similar to Enhancing Monotonicity for Robust Autoregressive Transformer TTS

34
/ 100
Emerging

This project helps create high-quality text-to-speech (TTS) systems by improving how spoken audio aligns with input text. It takes text encodings and mel-spectrogram encodings, then produces a text-audio fusion where the spoken words accurately match the original text. This is designed for engineers and researchers building robust neural TTS models.

No commits in the last 6 months.

Use this if you are developing an autoregressive text-to-speech system and need to ensure a strong, consistent alignment between the input text and the generated speech's mel-spectrogram.

Not ideal if your task does not involve sequence-to-sequence alignment for speech synthesis, as it's specifically tailored for text-to-audio matching.

text-to-speech speech-synthesis audio-alignment natural-language-processing voice-generation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

39

Forks

5

Language

Python

License

MIT

Last pushed

May 16, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/keonlee9420/Stepwise_Monotonic_Multihead_Attention"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.