Posted on Jul 16, 2021

Language Model Integration in Encoder-Decoder Speech Recognition

Posted in Machine Learning
photo of a motherboard

Currently, Attention-based recurrent Encoder-Decoder models provide an elegant way of building end-to-end models for different tasks, like automatic speech recognition (ASR), machine translation (MT), etc. An end-to-end ASR model folds traditional acoustic model, pronunciation model, and language model (LM) into a single network. An encoder maps the input speech to a sequence of higher-level...

Scroll to top