Lead Speech Scientist (Text-to-Speech)
Skills
AlgorithmsConversational AIGenerative AIPhoneticsSpeechSpeech RecognitionSpeech Synthesis
What the job involves
The main requirements, responsibilities and hiring steps.
Requirements
- Have over 4 years of hands-on experience in building algorithmic Speech Synthesis Models
- Possess an MSc or PhD in Speech & Signal Processing, Computational Linguistics, Computer Science, Data Science, or a related field
- Strongly understand speech and language processing, including phonetics, speech synthesis, recognition, and machine translation
- Capable of independent research with minimal supervision
- Proficient in Python coding
- Genuine enthusiasm for Text-to-Speech
Nice to have
- Collaborative
- Innovative
- Adaptable
Day to day
- Collaborate with a team to push the boundaries of Text-to-Speech and Speech Synthesis in Conversational AI.
- Build a TTS team from scratch, implementing SOTA Text-to-Speech models focusing on expressiveness and naturalness.
- Lead the strategy of the TTS team, hire necessary resources, and improve naturalness drastically over the next 12 months.