HaikuS2S: A Cascaded System For Responding In Verse

arXiv:2609.23951 · cs.CL, cs.AI, cs.SD · Submitted 2026-09-20 · Read on arXiv

cs.CL, cs.AI, cs.SD

Submitted: 2026-09-20

Updated: 2026-09-20

Comments: Accepted to SLT 2026, Demo Track. 5 pages, 5 figures

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Fine-Tuning — 14× in this paper · explained in 5 episodes
• Alignment — 10× in this paper · explained in 1 episode
• Embeddings — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes

Sources

• Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron
• PoeticTTS -- Controllable Poetry Reading for Literary Studies
• emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation
• MsEmoTTS: Multi-scale emotion transfer, prediction, and control for emotional speech synthesis
• iEmoTTS: Toward Robust Cross-Speaker Emotion Transfer and Control for Speech Synthesis based on Disentanglement between Prosody and Timbre
• Simple and Effective Multi-sentence TTS with Expressive and Coherent Prosody

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering