SoTA Speech

Il y a 2 jours

Paris, Île-de-France Institute of Foundation Models Temps plein 70 000 € - 120 000 €/an

Institute of Foundation Models is seeking a Research Scientist specializing in speech/audio machine learning to contribute to the design and training of SoTA end-to-end neural speech models. You will develop core intellectual property and move beyond cascaded ASR→TTS toward native audio-to-audio multimodal architectures.

Responsibilities include designing novel architectures, engineering loss functions for prosody and naturalness, and running large-scale experiments with rigorous evaluation