Preserving SENĆOŦEN: The Role of AI Speech to Text

Saanich, or SENĆOŦEN, is a Coast Salish language indigenous to the southern tip of Vancouver Island and the nearby Gulf Islands. It is a language of the Saanich people, with a rich oral tradition and a unique writing system. Today, with only a handful of fluent speakers, the language is critically endangered. Efforts to revitalize SENĆOŦEN include immersion programs, community classes, and digital documentation. One powerful tool in this effort is accurate speech to text technology.

Why Saanich Speech to Text Matters

Transcribing Saanich audio is essential for creating written records of oral stories, songs, and everyday conversations. These transcripts become the foundation for language learning materials, dictionaries, and cultural archives. However, Saanich poses unique challenges for automatic speech recognition (ASR). The orthography includes letters with diacritics and special characters that are absent from most ASR systems. Speechyou’s Saanich model is built from the ground up to handle these characters, ensuring that the output is faithful to the standard writing system.

Challenges in Saanich Transcription

• Phonological complexity: Saanich has a large inventory of consonants, including glottalized stops (e.g., Ḱ, Ⱦ) and lateral fricatives (e.g., Ł). These sounds are rare globally and require specialized acoustic modeling.
• Vowel length: Long and short vowels are phonemic, meaning they change word meaning. For example, 'TŦE' (the) versus 'TŦE·' (with a long vowel, a different word). Speechyou’s time-based modeling captures these distinctions.
• Dialectal variation: Northern and Southern Saanich differ in pronunciation and vocabulary. Speechyou allows users to specify dialect preferences or upload custom glossaries to improve accuracy.
• Low digital footprint: With few existing transcriptions, training data is scarce. Speechyou uses transfer learning from related languages and community-contributed data to overcome this.

Use Cases for Saanich Transcription

• Language revitalization: Transcribe elder interviews to create bilingual books and digital archives.
• Education: Generate subtitles for Saanich-language videos used in schools and immersion programs.
• Research: Linguists can analyze transcribed texts for phonetic and grammatical studies.
• Media production: Podcasters and filmmakers can add Saanich subtitles to reach wider audiences.
• Accessibility: Deaf and hard-of-hearing community members can access spoken Saanich content.
• Oral history preservation: Convert audio recordings of ceremonies and stories into searchable text.

How Speechyou Helps

Speechyou offers a dedicated Saanich speech to text model that supports the full SENĆOŦEN orthography. Users can upload audio or video files in common formats and receive transcriptions in minutes. The output can be exported as SRT or VTT subtitles, ready for use in video platforms or editing software. For the best results, we recommend clear recordings with minimal background noise and a single speaker. With Speechyou, the Saanich language gains a digital ally in its fight for survival.

Getting Started

To transcribe Saanich audio, simply sign up for a Speechyou account, choose the Saanich language model, and upload your file. Our AI processes the speech and returns a text transcription that you can edit, download, or share. Whether you are a community language worker, a teacher, or a researcher, Speechyou makes it easy to turn spoken SENĆOŦEN into written words.