NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
38 results for “keyword:"text to speech"” in ICLR 2027. 2 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Atom-TTS: A lightweight on-device TTS system adopting cascaded prediction and frame-driven vocoder▼1.2k1.67
[PDF]Input Embeddings as a Compositional Pronunciation Interface for Frozen LLM-Based Chinese TTS▼4.3k2.00
[PDF]CARE-Voice: Constraint-Aware Reliable Evaluation via Selective Decisions for Voice Design▼1361.33
[PDF]Structured Prosody Modeling for Long-Form Text-to-Speech via Semantic-Conditioned Cross-Scale Regularization▼13k2.00
[PDF]CoCiTTS: Towards Character-Level Speaker Consistency in Zero-Shot TTS for Cross-Lingual Cinematic Dubbing▲3.9k1.67
[PDF]ExpressTTS-Bench: Benchmarking the Scenario-based Expressiveness of Text-to-Speech Models▲6.1k2.00
[PDF]X-Emo: Disentangled Speech Tokens for Cross-Lingual Zero-Shot Expressive Text-to-Speech▲3.0k2.33
[PDF]Edit Who Speaks, Control How They Speak: Global Timbre Editing and Local Instruction Control for TTS▲3972.67
[PDF]Tacit-TTS: From Autoregressive Decoding to Masked Prediction for Efficient Transcript-Free Voice Cloning▼4.3k2.00
[PDF]DualRef-TTS: A Label-Free Dual-Reference Framework for Independent Style-Timbre Control in Zero-Shot Speech Synthesis▼1.2k1.67
[PDF]Same Words, Different Intent: Hostility-Conditioned Contrastive Learning for Robust Multilingual, Multimodal Hate Speech Detection▼4.3k2.00