Abstract: End-to-end (E2E) models, including the attention-based encoder-decoder (AED) models, have achieved promising performance on the automatic speech recognition (ASR) task. However, the ...

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 ...

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. The system ...

BiGRU encoder + Attention decoder, based on "Listen, Attend and Spell" 1. The acoustic features are 80-dimensional filter banks. They are stacked every 3 consecutive frames, so the time resolution is ...

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 ...

Many computational methods have been proposed to predict drug–drug interactions (DDIs), which can occur when combining drugs to treat various diseases, but most mainly utilize single-source features ...