We lifted 3 functions out of this paper's own repositories and ran 0 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 |
|---|---|---|
| nii-yamagishilab/multi-speaker-tacotron | canonical | 0 of 3 |
| Function | Status | Where it lives |
|---|---|---|
| expand_abbreviations | Not yet run | nii-yamagishilab/multi-speaker-tacotron/synthesize_new_texts/datasets/cleaners.py code served (permissive licence) · get_code("cea1f83e9db28ed8") |
| lowercase | Not yet run | nii-yamagishilab/multi-speaker-tacotron/synthesize_new_texts/datasets/cleaners.py code served (permissive licence) · get_code("296274b940cb0b32") |
| text_to_sequence | Not yet run | nii-yamagishilab/multi-speaker-tacotron/synthesize_new_texts/datasets/text.py code served (permissive licence) · get_code("702bf3362420114b") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Previous work on speaker adaptation for end-to-end speech synthesis still falls short in speaker similarity. We investigate an orthogonal approach to the current speaker adaptation paradigms, speaker augmentation, by creating artificial speakers and by taking advantage of low-quality data. The base Tacotron2 model is modified to account for the channel and dialect factors inherent in these corpora. In addition, we describe a warm-start training strategy that we adopted for Tacotron2 training. A large-scale listening test is conducted, and a distance metric is adopted to evaluate synthesis of dialects. This is followed by an analysis on synthesis quality, speaker and dialect similarity, and a remark on the effectiveness of our speaker augmentation approach. Audio samples are available online.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2005.01245")
get_code_for_paper("2005.01245")
have("2005.01245")
Connect an agent — have() is free.