IPA2WAV - A deep learning-based text-to-speech synthesis system that converts International Phonetic Alphabet (IPA) symbols to speech

Pytorch CNN Speech Synthesis Deep Learning Text-to-Speech

Authors

Moitree Basu

PhD [ML, Privacy, NLP]

---

← MANTIS [Multi-Architecture Neural Text Intelligence System] - A Named Entity Recognition (NER) and document type classification project that combines transformer-based models (BERT and T5) Jul 7, 2024

Grapheme-to-Phoneme Synthesis - An LSTM based model for machine translation applied to grapheme-to-phoneme synthesis. Apr 13, 2024 →