"Attention-Based Encoder-Decoder Model" · 2 results · Global ETD Search

Results

Showing 1 to 2 of 2 for “"Attention-Based Encoder-Decoder Model"”.

Attention-Based Encoder-Decoder Models for Speech Processing

Li, QiujiaUniversity of Cambridge2022

… Many speech processing problems are modelled using sequence-to-sequence models. More recently, the Attention-Based Encoder-Decoder (AED) model has become a general and effective neural network that transforms a source sequence into a target sequence. These two sequences may have …

cambridge Repository record for Attention-Based Encoder-Decoder Models for Speech Processing (opens in a new tab)
Data quality in the deep learning era: Active semi-supervised learning and text normalization for natural language understanding

Lourentzou, IsminiUniversity of Illinois at Urbana-Champaign2020

… or structured. In order for a machine learning model to be effective, volume is not the only data dimension that is necessary. Quality is equally important and has proven to be a critical factor for the success of industrial applications of machine learning. According to IBM, poor data quality …

uiuc Repository record for Data quality in the deep learning era: Active semi-supervised learning and text normalization for natural language understanding (opens in a new tab)