We lifted 2 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| keonlee9420/Cross-Speaker-Emotion-Transfer | pwc_unofficial | 2 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| get_padding | Ran | keonlee9420/Cross-Speaker-Emotion-Transfer/hifigan/models.py code served (permissive licence) · get_code("a26f85d7c72ef39a") |
| get_sinusoid_encoding_table | Ran | keonlee9420/Cross-Speaker-Emotion-Transfer/model/modules.py code served (permissive licence) · get_code("0f8f22937463d3c5") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
This paper introduces Parallel Tacotron 2, a non-autoregressive neural text-to-speech model with a fully differentiable duration model which does not require supervised duration signals. The duration model is based on a novel attention mechanism and an iterative reconstruction loss based on Soft Dynamic Time Warping, this model can learn token-frame alignments as well as token durations automatically. Experimental results show that Parallel Tacotron 2 outperforms baselines in subjective naturalness in several diverse multi speaker evaluations. Its duration control capability is also demonstrated.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2103.14574")
get_code_for_paper("2103.14574")
have("2103.14574")
Connect an agent — have() is free.