SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.08810 · 2023

Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 3 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.

RepositoryRoleRan
yl4579/pl-bert pwc_unofficial 3 of 6
FunctionStatusWhere it lives
build_dataloader Ran yl4579/pl-bert/simple_loader.py
code served (permissive licence) · get_code("164d730b65626a89")
length_to_mask Ran yl4579/pl-bert/utils.py
code served (permissive licence) · get_code("c992f7522596af60")
remove_accents Ran yl4579/pl-bert/text_normalize.py
code served (permissive licence) · get_code("09fd0528a6789379")
normalize_split Not yet run yl4579/pl-bert/text_normalize.py
code served (permissive licence) · get_code("24ba5ac0d31cfc90")
scan_checkpoint Not yet run yl4579/pl-bert/utils.py
code served (permissive licence) · get_code("a78ec371614680b0")
split_given_size Not yet run yl4579/pl-bert/text_normalize.py
code served (permissive licence) · get_code("4eb9eab560b3a8e9")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large-scale pre-trained language models have been shown to be helpful in improving the naturalness of text-to-speech (TTS) models by enabling them to produce more naturalistic prosodic patterns. However, these models are usually word-level or sup-phoneme-level and jointly trained with phonemes, making them inefficient for the downstream TTS task where only phonemes are needed. In this work, we propose a phoneme-level BERT (PL-BERT) with a pretext task of predicting the corresponding graphemes along with the regular masked phoneme predictions. Subjective evaluations show that our phoneme-level BERT encoder has significantly improved the mean opinion scores (MOS) of rated naturalness of synthesized speech compared with the state-of-the-art (SOTA) StyleTTS baseline on out-of-distribution (OOD) texts.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2301.08810")
get_code_for_paper("2301.08810")
have("2301.08810")

Connect an agent — have() is free.