Language Independent End-to-End Architecture For Joint Language and Speech Recognition

By Takaaki Hori, John R. Hershey

Subfields: Natural Language Processing, Speech & Audio

Citations in the corpus

• Multilingual Speech Recognition with a Single End-to-End Model (2017, neutral): “Our work is most similar to that of [12] which similarly proposes an end-to-end trained multilingual recognizer to directly predict grapheme sequences in 10 distantly related languages.”