AI/ML – Voice Building Engineer, Siri Text-to-Speech

Job Overview

Key Qualifications

Experience in voice building, testing, and tuning pronunciation, normalization and/or other text processing models

Ability to implement experiments using scripting languages (Python, bash) and tools written in C/C++

Solid Understanding or experience working with standard ML algorithms and toolkits

Solid understanding of phonetic notation such as IPA, SAMPA or CMU

Ability to create, analyze and optimize voice talent recording scripts and other text corpora for areas such as phonetic and prosodic coverage

3-5 years experience working in text-to-speech, speech recognition or related fields

Description

The Siri Text-to-Speech team is looking for Voice Building Engineers to take part in building the voice of Siri. You’ll develop and fine-tune ML models used in TTS text processing and backend TTS models for Siri voices. You’ll also analyze errors and use your high-quality analysis to develop systemic issues on Siri voices in particular locales. Lastly, you’ll implement your ideas directly in our TTS engine or tools. Hundreds of millions of users will experience your contributions through more natural and expressive Siri voices on Apple products.

Education & Experience

Master’s degree or higher in Computer Science, Computational Linguistics or a related field

View More