AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Hierarchical Semantic-Acoustic Modeling via Semi-Discrete Residual Representations for Expressive End-to-End Speech Synthesis

Yixuan Zhou, Guoyang Zeng, Xin Liu, Xiang Li, Renjie Yu, Ziyang Wang, Runchuan Ye, Weiyue Sun, Jiancheng Gui, Kehan Li, Zhiyong Wu, Zhiyuan Liu

ICLR 2026 · Image generation › Autoregressive and latent generation · approach: Neural text-to-speech synthesis

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
add FSQ semi-discrete bottleneck (vs purely continuous) (ablation)VoxCPM · ZH-hard (ablation)CER (%): 24.92 -> 18.19Improved
add RALM residual acoustic model (ablation)VoxCPM · EN (ablation)WER (%): 4.34 -> 2.98Improved
increase single-stream TSLM capacity from 24 to 30 layers (no RALM) (ablation)w/o RALM variant · EN (ablation)WER (%): 4.34 -> 4.12No clear effect
add pre-trained text LM init to TSLM (ablation)VoxCPM · EN (ablation)WER (%): 5.24 -> 2.98Improved
add original acoustic embeddings input to RALM (ablation)VoxCPM · EN (ablation)WER (%): 4.91 -> 2.98Improved
add residual hidden state in LocDiT condition (ablation)VoxCPM · EN (ablation)WER (%): 3.86 -> 2.98Improved
FSQ dimension 4 instead of 256 (ablation)VoxCPM · EN (ablation)WER (%): 2.98 -> 5.18Hurt
FSQ dimension 128 instead of 256 (ablation)VoxCPM · ZH-hard (ablation)CER (%): 18.19 -> 16.76Mixed
replace sum fusion with attention fusion (ablation)LocDiT conditioning · EN (ablation)WER (%): 2.98 -> 4.92Hurt
replace sum fusion with concatenation (ablation)LocDiT conditioning · ZH (ablation)CER (%): 1.77 -> 2.88Mixed
remove classifier-free guidance (CFG 1.0 vs 2.0) (ablation)VoxCPM · Seed-TTS-eval ENWER (%): 1.85 -> 16.32Hurt
raise CFG from 2.0 to 5.0 (ablation)VoxCPM · Seed-TTS-eval ENWER (%): 1.85 -> 12.78Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

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