no code implementations • 20 Sep 2021 • Joan Codina-Filbà, Guillermo Cámbara, Jordi Luque, Mireia Farrús
Furthermore, we study the influence of a language model -- which tends to correct non-standard sequences of words -- with the lack of language model to decode the hypothesis from the ASR.
no code implementations • 18 Nov 2020 • Mireia Farrús, Joan Codina-Filbà
Both tasks have been performed extracting 28 features from speech -- based on prosody and voice quality -- and 51 features from the transcriptions -- based on lexical and turn-taking information.