Job Description
A Moving Experience.
Representative responsibilities/duties will include but not limited to:
·Design and optimize text/NLP preprocessing pipelines with Deep Learning or Machine Learning methods, including Grapheme-to-phoneme (G2P) conversion for multilingual support; Text normalization; polyphone disambiguation; Prosody prediction and control
·Integrate language models (e.g., BERT, GPT variants) to improve contextual and semantic understanding for natural intonation
·Develop rule-based and neural solutions for emotion/style control in synthesized speech
·Build state-of-the-art acoustic models (e.g., Tacotron, FastSpeech, VITS) to map linguistic features to spectrograms or waveform parameters.
·Optimize neural vocoders (e.g., WaveNet, HiFi-GAN, MelGAN, LPCNet) for high-fidelity, real-time speech synthesis
·Optimize inference latencies for both edge devices and cloud platforms
·Enhance robustness through noise supp...