Multilingual TTS Synthesis

TTS: Text-to-Speech

Follow this topic Ask about this topic

Latest papers

21 papers2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

SEAM: Spectral Embedding Alignment and Merging for Low-Resource TTS
Oct 19, 2026Walaa Othman, Baher Mohammad, Stamatios Lefkimmiatis +1Text-to-Speech Low-Resource TTS Synthesis
ITMO University · SPC RAS · MWS AI
Cross-Lingual TTS for Indian Languages: A Benchmark and Inference-Time Duration Estimation Strategies
Oct 10, 2026Adarsh Arigala, Arjun Gangwar, Srinivasan UmeshMultilingual TTS Synthesis TTS Synthesis
SPRING Lab, Indian Institute of Technology Madras, India
Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning
Sep 24, 2026Yoomee Cho, Jisun LeeTTS Synthesis Multilingual TTS Synthesis
ESTsoft, Seoul, Republic of Korea
Tone on a Budget: A Reference-Free Metric for Lexical Tone in Massively Multilingual Text-to-Speech
Sep 13, 2026Moses Daudu, Adeola Enitan Bamidele, Honor-Jesus BezaleelTTS Synthesis TTS Evaluation
Landmark University, Omu-Aran, Nigeria · Federal University of Agriculture, Abeokuta, Nigeria · Independent Researcher
Complex-Text Robustness Evaluation and Failure Diagnosis for Low-Resource Multilingual Text-to-Speech
Sep 10, 2026Tianlun Zuo, Ziyu Zhang, Tingzhi Mao +2TTS Synthesis TTS Evaluation
iFLYTEK Company Ltd., Xi’an, China
Confucius4-TTS: Transcript-Free Cross-Lingual Zero-Shot TTS with a Learnable Speaker Encoder
Aug 12, 2026Huaxuan Wang, Huimin Wang, Ruiyu Zhang +2TTS Synthesis Multilingual TTS Synthesis
NetEase Youdao, Beijing, China
CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations
Jun 24, 2026Ram Annamdevula, Ankit Tatawat, Ashishkumar P. Gudmalwar +2Disentangled Representation Learning TTS Synthesis
Media Analysis, Sony Research India
UR-BERT: Scaling Text Encoders for Massively Multilingual TTS Through Universal Romanization and Speech Token Prediction
Jun 10, 2026Sangmin Lee, Eekgyun Ahn, Woongjib Choi +1TTS Synthesis Multilingual TTS Synthesis
Dept. of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea
OpenBibleTTS: Large-Scale Speech Resources and TTS Models for Low-Resource Languages
Jun 8, 2026David Guzmán, Luel Hagos Beyene, Jesujoba Oluwadara Alabi +3TTS Synthesis TTS Evaluation
McGill University · Mila - Quebec AI Institute · AIMS Research and Innovation Centre +3
Pixel-TTS: Image based Text Rendering for Robust Text-to-Speech
Jun 5, 2026Adarsh Arigala, Arjun Gangwar, S Umesh +1TTS Synthesis Multilingual TTS Synthesis
SPRING Lab, Indian Institute of Technology, Madras, India · 2MBZUAI, UAE
dots.tts Technical Report
Jun 5, 2026Shi Lian, Changtao Li, Bohan Li +6TTS Synthesis Speech Foundation Models
VoxCPM2 Technical Report
Jun 5, 2026Yixuan Zhou, Guoyang Zeng, Xin Liu +15Speech Foundation Models Multilingual TTS Synthesis
VoxCPM Team
Multilingual Multi-Speaker Unit Vocoders: A Systematic Analysis of Discrete Speech Representations
Jun 4, 2026Naman Kothari, Arjun Gangwar, Adarsh Arigala +1TTS Synthesis Multilingual TTS Synthesis
National Institute of Technology, Trichy · Indian Institute of Technology, Madras
X-Voice: Enabling Everyone to Speak 30 Languages via Zero-Shot Cross-Lingual Voice Cloning
May 7, 2026Rixi Xu, Qingyu Liu, Haitao Li +10TTS Synthesis Zero-Shot TTS
1MoE Key Lab of Artificial Intelligence, X-LANCE Lab, Shanghai Jiao Tong University · Center for Language and Speech Processing, Johns Hopkins University · 2Shanghai Innovation Institute +4
Praxy Voice: Voice-Prompt Recovery + BUPS for Commercial-Class Indic TTS from a Frozen Non-Indic Base at Zero Commercial-Training-Data Cost
Apr 28, 2026Venkata Pushpak Teja MentaTTS Synthesis Multilingual TTS Synthesis
Praxel Ventures
MINT-Bench: A Comprehensive Multilingual Benchmark for Instruction-Following Text-to-Speech
Apr 20, 2026Huakang Chen, Jingbin Hu, Liumeng Xue +12TTS Synthesis Speech Generation Evaluation
School of Intelligence Science and Technology, Nanjing University, Suzhou, China · Yutu Zhineng, Beijing, China · Lingguang Zhaxian Technology, Shanghai, China
Giving Voice to the Constitution: Low-Resource Text-to-Speech for Quechua and Spanish Using a Bilingual Legal Corpus
Apr 14, 2026John E. Ortega, Rodolfo Zevallos, Fabricio CarraroMultilingual TTS Synthesis TTS Synthesis
Northeastern University, USA · Universitat Pompeu Fabre, Spain · Barcelona Supercomputing Center, Spain
OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models
Apr 1, 2026Han Zhu, Lingxuan Ye, Wei Kang +7Multilingual TTS Synthesis TTS Synthesis
Xiaomi Corp., China
Voxtral TTS
Mar 26, 2026Mistral-AI, :, Alexander H. Liu +186Multilingual TTS Synthesis TTS Synthesis
Accent Vector: Controllable Accent Manipulation for Multilingual TTS Without Accented Data
Mar 8, 2026Thanathai Lertpetchpun, Thanapat Trachu, Jihwan Lee +3Multilingual TTS Synthesis TTS Synthesis
Signal Analysis and Interpretation Lab, University of Southern California, USA · Thomas Lord Department of Computer Science, University of Southern California, USA · Department of Linguistics, University of Southern California
UtterTune: LoRA-Based Target-Language Pronunciation Edit and Control in Multilingual Text-to-Speech
Aug 13, 2025Shuhei KatoTTS Synthesis Multilingual TTS Synthesis
Independent Researcher Tokyo, Japan

Oct 19, 2026J/K move · Enter open · S save

SEAM: Spectral Embedding Alignment and Merging for Low-Resource TTS

Walaa Othman, Baher Mohammad, Stamatios Lefkimmiatis, Ammar Ali

ITMO University · SPC RAS · MWS AI

Text-to-Speech Low-Resource TTS Synthesis Multilingual TTS Synthesis

Open paper AskPDF arXiv

Expanding the vocabulary of conditional text-to-speech (TTS) models typically requires extensive fine-tuning with paired audio, creating a major bottleneck for low-resource and cross-lingual adaptation. To address this, we introduce SEAM, a zero-audio initialization method that constructs embeddings for unseen tokens from known subtokens. Unlike standard pooling strategies that ignore sequential structure, SEAM applies a spectral filter to preserve temporal phonetic order and uses closed-form ridge regression to align the new embeddings with the pretrained conditioning manifold. Across three languages and two TTS architectures, SEAM approaches or matches baseline performance using up to four times less training data, reducing sample complexity by 75% compared to random initialization and mean pooling. Our approach provides a lightweight, reproducible, and theoretically grounded solution for vocabulary expansion in low-resource speech synthesis.