We explore contextual biasing with Large Language Models (LLMs) to enhance Automatic
Speech Recognition (ASR) in second-pass rescoring. Our approach introduces the utilization …

Recently, there has been an increasing interest in two-pass streaming end-to-end speech
recognition (ASR) that incorporates a 2nd-pass rescoring model on top of the conventional 1st-…

This paper discusses the challenges of optical character recognition (OCR) on natural
scenes, which is harder than OCR on documents due to the wild content and various image …

Global climate models (GCMs) provide most climate change projections, but their coarse
resolution must be downscaled to more local scales in order to conduct meaningful climate …

Soft Actor-Critic (SAC) is a state of the art offpolicy algorithm for deep reinforcement learning;
however, little exploration into a critical component of the algorithm, experience replay, has …

We present a series of programming assignments, adaptable to a range of experience levels
from advanced undergraduate to PhD, to teach students design and implementation of …

We introduce Lumos, the first end-to-end multimodal question-answering system with text
understanding capabilities. At the core of Lumos is a Scene Text Recognition (STR) …

Rad razmatra primjenu sustava RFID u proizvodnji kabela. Prvi dio rada opisuje električne
kabele i njihovo tržište s posebnim naglaskom na Istočnu Europu. Dan je opis tvornice ELKA …

Bakalářská práce Pomáhání z pohledu křesťanské morálky se zabývá významem pomáhání
v křesťanské kultuře, která vychází z učení Ježíše Krista. Popisuje historii křesťanské charity …

Welcome to the Fifth Workshop on Teaching Natural Language Processing (NLP). This online
workshop featured an exciting mix of papers, teaching material submissions, panels, talks, …