AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

RobuTrans: A Robust Transformer-Based Text-to-Speech Model

Naihan Li, Yanqing Liu, Yu Wu, Shujie Liu, Sheng Zhao, Ming Liu

AAAI 2020 · Architectures and efficiency › Attention and transformers · approach: Long-context KV and memory attention · 37 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
replace encoder-decoder soft attention with duration-based hard attention plus PNCA, no position embeddingTransformerTTS · Bad-case setbad cases: 237 -> 0Improved
RobuTrans vs TransformerTTS naturalnessRobuTrans · General setMOS: 4.37 -> 4.36No clear effect
RobuTrans vs FastSpeech naturalnessRobuTrans · General setCMOS: +0.187Improved
add pseudo non-causal attention (vs causal self-attention) (ablation)RobuTrans · General setCMOS: -0.291 CMOS when removedImproved
add prosodic features (ablation)RobuTrans · General setCMOS: -0.134 CMOS when removedImproved
add linguistic (phonemic+prosodic) features to input (ablation)TransformerTTS · General setCMOS: -0.047Hurt
use forward/GMM/monotonic/guided attention instead of hard duration attentionTransformerTTS · Bad-case setbad casesNo clear effect

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