Phonetician, Linguist – Spanish-US

This is a fully remote position, open to applicants in Arizona, +4 more states.

📋 Description

• Ensure the linguistic and phonetic excellence of Omilia’s multilingual Text-to-Speech (TTS) systems by crafting phoneme inventories, developing lexicons, and reviewing audio corpora.

• Conduct detailed phonological and phonetic analysis of the American Spanish language.

• Document language-specific characteristics such as prosody, stress, tone, coarticulation, and dialect variation.

• Create structured language profiles for training and evaluating TTS models.

• Define and uphold phoneme inventories, while mapping to IPA and TTS-specific conventions.

• Perform audits on corpora and select optimal audio references for tuning TTS target voices.

• Build and manage pronunciation lexicons, incorporating G2P rules and exceptions.

• Review and rectify machine-generated G2P outputs and conduct pronunciation audits.

• Annotate audio corpora, develop evaluation protocols, and carry out error analyses.

• Establish linguistic criteria for TTS corpus selection and create prompts for data collection.

• Collaborate with TTS engineers to integrate linguistic artifacts into synthesis pipelines.

• Contribute to internal documentation and engage in research discussions.

⛳️ Requirements

• M.Sc. or Ph.D. in Linguistics, Phonetics, Computational Linguistics, or a related discipline.

• Demonstrated experience in constructing pronunciation lexicons or G2P systems for TTS or ASR.

• Comprehensive knowledge of phonological theory, along with articulatory and acoustic phonetics.

• Proficient in IPA and at least one machine-readable phoneme notation system (such as X-SAMPA, ARPAbet, etc.).

• Familiarity with corpus annotation tools (including Praat, ELAN, WebAnno, etc.).

• Strong analytical abilities and documentation skills.

• Fluency in English; proficiency in at least one additional language relevant to Omilia’s markets.

• Technical skills: proficiency in Praat, ELAN, Audacity, PLS/CMUdict/SSML lexicon formats, Phonetisaurus/Sequitur/neural G2P, and basic Python or shell scripting, as well as TTS text normalization.

🏝️ Benefits

• Fixed compensation;

• Long-term employment with vacation days;

• Opportunities for professional development (courses, training, etc.);

• Being part of innovative technology products that are making a global impact in the service industry;

• Collaborative and enjoyable colleagues;

• Apple equipment provided.