AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech

Rongjie Huang, Yi Ren, Jinglin Liu, Chenye Cui, Zhou Zhao

NeurIPS 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Zero-shot robustness and transfer · 21 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use GenerSpeech instead of FG-TransformerTTSOOD style transfer · VCTK, parallelMOS: 3.95 ± 0.1 -> 4.06 ± 0.08Improved
Use GenerSpeech instead of Meta-StyleSpeechOOD style transfer · VCTK, parallelSMOS: 3.95 ± 0.08 -> 4.01 ± 0.09Improved
Use GenerSpeech instead of FG-TransformerTTSOOD style transfer · VCTK, parallelCos: 0.86 -> 0.88Improved
Use GenerSpeech instead of FG-TransformerTTSOOD style transfer · VCTK, parallelFFE: 0.30 -> 0.35Hurt
Use GenerSpeech instead of Expressive FS2OOD style transfer · ESD, parallelMOS: 4.04 ± 0.08 -> 4.11 ± 0.10Improved
Use GenerSpeech instead of StylerOOD style transfer · ESD, parallelSMOS: 4.05 ± 0.08 -> 4.20 ± 0.09Improved
Use GenerSpeech instead of Expressive FS2OOD style transfer · ESD, parallelCos: 0.93 -> 0.97Improved
Use GenerSpeech instead of MellotronOOD style transfer · ESD, parallelFFE: 0.27 -> 0.26Improved
Add the multi-level local style encoder (ablation)GenerSpeech · Ablation evaluationCMOS: 0.0 vs -0.02Improved
Add the multi-level local style encoder (ablation)GenerSpeech · Ablation evaluationCSMOS: 0.0 vs -0.15Improved
Use Mix-Style layer normalization instead of original layer normalization (ablation)GenerSpeech · Ablation evaluationCMOS: 0.0 vs -0.06Improved
Use Mix-Style layer normalization instead of original layer normalization (ablation)GenerSpeech · Ablation evaluationCSMOS: 0.0 vs -0.07Improved

Later papers that compared with this method

1 later accepted paper reports GenerSpeech as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy