AssemblyAI Research
and Updates

A Survey on End-To-End Speech Recognition Architectures in 2021

As we continue our core research and development efforts to push the boundaries of state of the art accuracy, we begin exploring architectures for end-to-end speech recognition that are gaining relative new popularity, not only in the research domain but also in production settings in industry. We are specially interested in architectures that have shown production level accuracy matching or surpassing that of conventional hybrid DNN-HMM speech recognition systems. With that in mind, we survey the following two architectures: Listen Attend and Spell, and Recurrent Neural Network Transducers.

Building an end-to-end Speech Recognition model in PyTorch

In this blog post, we'll walk through how one would build their own end-to-end speech recognition model in PyTorch. The model we'll build is inspired by Deep Speech 2 (Baidu's second revision of their now-famous model) with some personal improvements to the architecture. The output of the model will be a probability matrix of characters, and we'll use that probability matrix to decode the most likely characters spoken from the audio.

Speaker Diarization: Speaker Labels for Mono Channel Files

Speaker diarization (diarisation) is the process of splitting audio or video inputs automatically based on the speaker's identity. It helps you answer the question "who spoke when?".