Leveraging Visemes for Better Visual Speech Representation and Lip Reading

no code implementations • 19 Jul 2023 • Javad Peymanfard, Vahid Saeedi, Mohammad Reza Mohammadi, Hossein Zeinali, Nasser Mozayani

We evaluate our approach on various tasks, including word-level and sentence-level lip reading, and audiovisual speech recognition using the Arman-AV dataset, a largescale Persian corpus.

Lip Reading Sentence +2

ArmanTTS single-speaker Persian dataset

no code implementations • 7 Apr 2023 • Mohammd Hasan Shamgholi, Vahid Saeedi, Javad Peymanfard, Leila Alhabib, Hossein Zeinali

TTS, or text-to-speech, is a complicated process that can be accomplished through appropriate modeling using deep learning methods.