End-to-end automatic speech recognition (ASR) systems have gained popularity given their simplified architecture and promising results. However, text-only domain adaptation remains a big challenge for ...

Project Overview The goal of this project is to implement a Transformer-based model for speech-to-text transcription, following an encoder-decoder architecture with multi-head attention mechanisms.

To fill this gap, we propose two attention-mechanism-based encoder–decoder models that incorporate multisource information: one is MAEDDI, which can predict DDIs, and the other is MAEDDIE, which can ...

Modern systems for automatic speech recognition, including the RNN-Transducer and Attention-based Encoder-Decoder (AED), are designed so that the encoder is not required to alter the time-position of ...

Although encoder-decoder networks with attention have achieved impressive results in many sequence-to-sequence tasks, the mechanisms behind such networks’ generation of appropriate attention matrices ...

For the project: Attention-based End-to-End Speech-to-Text Deep Neural Network, as part of homework 4 under the course 11-785: Intro to Deep Learning @ CMU 2022 Fall. - ...

Factorized AED: Factorized Attention-Based Encoder-Decoder for Text-Only Domain Adaptive ASR Abstract: End-to-end automatic speech recognition (ASR) systems have gained popularity given their ...