Internship - Machine Learning Research - Speech-to-Speech Translation
Core
Research intern exploring open problems in speech-to-speech translation, focusing on end-to-end models for real-time, natural cross-language conversation.
Role type
Research intern (PhD/Master's level)
Builds
End-to-end speech-to-speech translation models
Domain
AI, Speech Processing, Machine Translation
Deliverable
research
Required skills
deep learning, speech recognition, speech synthesis, machine translation, NLP, multimodal learning, PyTorch, JAX, TensorFlow, Python
Preferred skills
speech-to-speech translation, end-to-end streaming, neural TTS, speech tokenizers, audio codecs, large language models, multimodal models, speech evaluation metrics
Technologies
PyTorch, JAX, TensorFlow
Responsibilities
Define research questions and propose approaches, design and run experiments on large-scale models, analyze results, write up work for publication
Seniority
Intern
