The Speech Synthesis Workshop (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.

“Scaling down: sustainable synthesis for language diversity”

The theme of this edition of SSW is “Scaling down: sustainable synthesis for language diversity”. In line with this theme, the challenge focuses on synthesizing speech for Bildts, a unique language variety from the Netherlands.

SSW welcomes contributions not only in the core TTS technology but also gathers researchers from contributing sciences: from phoneticians, phonologists, linguists, neuroscientists to experts of multimodal human-machine interaction.

Since 1990, SSWs are held every three years under the auspices of ISCA‘s special interest group SynSIG. In 2019, it was decided to have an SSW every two years, since the technology is advancing faster these days.

The 13th ISCA Speech Synthesis Workshop will be held in  Leeuwarden, Netherlands, 24 (Sun)- 26 (Tue) Aug 2025. The worshop is a satellite event of the INTERSPEECH 2025 conference (Rotterdam, Netherlands).

Bildts

Bildts (Indo-European > West Germanic) is spoken in Het Bildt, a region in the Dutch province of Friesland. With approximately 10,000 first and second language speakers, it represents a vibrant example of European linguistic diversity. The language variety has been systematically through grammatical descriptions, dictionaries with pronunciation information, literary works, media productions (weekly radio broadcasts, theater performances), and regular newspaper columns.

For the Blizzard Challenge 2025, we have curated a dataset of high-quality audio recordings with corresponding linguistic resources. This choice of Bildts aligns with our theme of “sustainable synthesis for language diversity” – it presents participants with the real-world challenge of developing synthesis capabilities for a well-documented but data-limited language variety, representative of the thousands of smaller languages that could benefit from speech technology. The challenge is composed of two tasks:

• the traditional hub which this year consists of creating a synthetic voice for Bildts using the data
• a Zeroshot TTS for Bildts for different speakers with reference audio files provided during the release of the test set

Organisation

The 13th Speech Synthesis Workshop (SSW 2025) brings together experts from the University of Groningen, University of Helsinki, KTH Royal Institute of Technology, and the Mercator European Research Centre on Multilingualism and Language Learning. Our organizing team combines expertise in speech technology, linguistics, and minority language preservation to create a unique forum for advancing speech synthesis research.

read more.