Long-Form TTS Synthesis

TTS: Text-to-Speech

Latest papers

10 papers4 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Speaking Longer Than Learned: Training-Free Long-Form Generation for Full-Stream Text-to-Speech
Oct 14, 2026Jeseung Lim, Jiseong Woo, Heeseung KimLong-Form TTS Synthesis TTS Synthesis
Department of Physics, University of Seoul, Seoul, Republic of Korea · Department of AI, University of Seoul, Seoul, Republic of Korea
A Comprehensive Objective Evaluation of Modern Text-to-Speech for Turkish Using Speech Quality Assessment Models
Oct 5, 2026Yunus Emre Ozkose, Alperen Kahraman, Ali HaznedarogluTTS Synthesis TTS Evaluation
Sestek, Ankara, Türkiye
Balalaika-Longform: A Russian Speech Corpus for Continuous Long-Form Text-to-Speech
Sep 30, 2026Nikita Vasiliev, Kirill Borodin, Vasilii Kudryavtsev +2TTS Synthesis TTS Evaluation
BitmanagerAI, Dubai, UAE · lab260, Yerevan, Armenia · MTUCI, Moscow, Russia
BanglaKontho: Closing the Long-Form Gap in Bangla Text-to-Speech
Sep 24, 2026Mizbaul Haque MarufTTS Synthesis Low-Resource TTS Synthesis
Vivasoft Limited, Dhaka, Bangladesh
Taming Long-form Text-to-Speech
Sep 15, 2026Rongxiang Wang, Berkin Durmus, Aysegul Orhon +2TTS Synthesis TTS Evaluation
Argmax, Inc. · University of Virginia · Bilkent University
TontaubeV1: Streaming Text-to-Speech with Hierarchical Codec Modeling and Bounded Context
Sep 8, 2026Fritz Cremer, Jonathan CremerTTS Synthesis Streaming TTS Synthesis
SceneTTS-Bench: A Benchmark for Scene-Level TTS in Drama Dubbing
Aug 13, 2026Yizhong Geng, Yanliang Li, Jinghan Yang +3Long-Form TTS Synthesis TTS Synthesis
Beijing University of Posts and Telecommunications Beijing, China · Beijing DeepLogic Intelligence Technology Co., Ltd. Beijing, China · University of California USA
MagpieTTS-LF: Inference-Time Long-Form Speech Generation Without Training on Long-Form data
Jun 16, 2026Subhankar Ghosh, Jason Li, Paarth Neekhara +4TTS Synthesis Speech Prosody
NVIDIA Corporation, USA
Borderless Long Speech Synthesis
Mar 20, 2026Xingchen Song, Di Wu, Dinghao Zhou +12Multi-Speaker TTS Long-Form Speech Recognition
MiLM Plus, Xiaomi Inc., China · WeNet Open Source Community · Nanjing University, China
Prosodic Boundary-Aware Streaming Generation for LLM-Based TTS with Streaming Text Input
Mar 6, 2026Changsong Liu, Tianrui Wang, Ye Ni +2Long-Form TTS Synthesis TTS Synthesis
Nanyang Technological University, Singapore · Tianjin University, China · Southeast University, China

Oct 14, 2026J/K move · Enter open · S save

Speaking Longer Than Learned: Training-Free Long-Form Generation for Full-Stream Text-to-Speech

Jeseung Lim, Jiseong Woo, Heeseung Kim

Department of Physics, University of Seoul, Seoul, Republic of Korea · Department of AI, University of Seoul, Seoul, Republic of Korea

Long-Form TTS Synthesis TTS Synthesis Streaming TTS Synthesis Length Generalization Sliding-Window Attention TTS Evaluation

Open paper AskPDF arXiv

Recent full-stream text-to-speech (TTS) models enable low-latency personalized synthesis as input text arrives. However, sustaining generation beyond the lengths seen during training without additional training remains largely unexplored. We systematically analyze VoXtream2, which extends generation by periodically discarding past context while retaining the acoustic prompt. We find that this strategy does not prevent degradation: pronunciation accuracy deteriorates near the end of the training range due to the range of positions in which the model operates rather than the loss of past context, while speaker similarity gradually declines throughout generation. Based on these findings, we propose two training-free modifications that reduce the attention window and strengthen attention to the acoustic prompt. Experiments show that these modifications preserve pronunciation accuracy and speaker similarity throughout long-form generation while retaining the naturalness of the original model. Ablations further show complementary effects of the two modifications.