no code implementations • 26 Jan 2024 • Md Mushfiqur Rahman, Mohammad Sabik Irbaz, Kai North, Michelle S. Williams, Marcos Zampieri, Kevin Lybarger
Our innovative RLHF reward function surpassed existing RL text simplification reward functions in effectiveness.
1 code implementation • 17 Oct 2023 • Fardin Ahsan Sakib, A H M Rezaul Karim, Saadat Hasan Khan, Md Mushfiqur Rahman
As voice assistants cement their place in our technologically advanced society, there remains a need to cater to the diverse linguistic landscape, including colloquial forms of low-resource languages.
1 code implementation • 12 Oct 2023 • Md Mushfiqur Rahman, Fardin Ahsan Sakib, Fahim Faisal, Antonios Anastasopoulos
To understand the downstream implications of text representation choices, we perform a comparative analysis on language models having diverse text representation modalities including 2 segmentation-based models (\texttt{BERT}, \texttt{mBERT}), 1 image-based model (\texttt{PIXEL}), and 1 character-level model (\texttt{CANINE}).
1 code implementation • EURASIP Journal on Audio, Speech, and Music Processing 2020 • Alif Bin Abdul Qayyum, K. M. Naimul Hassan, Adrita Anika, Md. Farhan Shadiq, Md Mushfiqur Rahman, Md. Tariqul Islam, Sheikh Asif Imran, Shahruk Hossain, Mohammad Ariful Haque
DOANet is based on a one-dimensional dilated convolutional neural network that computes the azimuth and elevation angles of the target sound source from the raw audio signal.