13th ISCA Speech Synthesis Workshop (SSW13) - 24-26 August 2025 in Leeuwarden, NL - <https://blogs.helsinki.fi/ssw13-2025/>

We are delighted to announce the 13th edition of the Speech Synthesis Workshop (SSW) which will take place in Leeuwarden (the Netherlands), from Sunday the 24th till Wednesday the 26th of August 2025. The workshop is a satellite event of the Interspeech 2025 conference (held in Rotterdam, the Netherlands).

The SSW is the main meeting place for research and innovation in speech synthesis, i.e. predicting speech signals from text input. Text-to-Speech (TTS) technology is a key component of numerous applications: speech-to-speech translation, digital assistants, conversational agents, social robots. While early research focused on basic intelligibility, contemporary systems now achieve remarkable naturalness. Current research frontiers include emotional expression, speaking style control, and efficient deployment for the world's languages.

**Theme: Scaling down: Sustainable synthesis for language diversity**

SSW13 focuses on making speech synthesis more accessible for the world's languages. We encourage submissions addressing:

- Data-efficient methods for low-resource languages
- Computationally sustainable approaches
- Cross-lingual transfer learning
- Language-specific challenges in TTS


= Key Information =

- Paper Format: Up to 6 pages including references using the Interspeech 2025 template
- Review Process: Double-blind peer review
- Presentation format: Oral and poster sessions
- Virtual Participation: None, in-person only

= Important Dates =

- January 30, 2025: Submission site opens
- **April 1, 2025: Initial submission deadline (title/abstract/authors)**
- April 14, 2025: Full paper deadline
- June 14, 2025: Notification of acceptance
- June 28, 2025: Camera-ready deadline
- August 17-22, 2025: Interspeech (Rotterdam)
- August 24-26, 2025: SSW13 (Leeuwarden)


= Topics =

SSW welcomes contributions not only in the core TTS technology but also includes researchers from related science -- from phoneticians, phonologists, and neuroscientists to experts of multimodal human-machine interaction.


Core tech
- End-to-end text-to-speech synthesis
- Direct waveform generation
- Voice conversion and modification
- Multilingual/cross-lingual synthesis
- Low-resource TTS methods


Linguistic aspects
- Text normalization and preprocessing
- Prosody modeling
- Expression and emotion
- Natural language generation for TTS
- G2P conversion


Applications & eval
- Speech synthesis for accessibility
- Embedded/edge deployment
- Quality assessment metrics
- Privacy and security
- Ethical considerations


Special applications
- Singing synthesis
- Non-human vocalization
- Talking faces/avatars
- Clinical applications