import { Link } from 'react-router-dom' import { Button } from 'semantic-ui-react' {% extends 'mainTemplate.html' %} {% block banner %}

Multi-speaker detection in your audio recordings.

Do you want to have a try?

Let's go upload!
{% endblock banner %}

We Help Companies and Companions

We can give your company superpowers to do things that they never thought possible. Let us delight your customers and empower your needs...through pure data analytics.

We Make Bananas That Can Dance

Yes that's right, you thought it was the stuff of dreams, but even bananas can be bioengineered.

{% block content %}

Project Description

Overall

Our project aims to achieve multi-speaker speech recognition for the Data Observatory Voice Bot developed at Imperial College London. When multiple people talk to the voice bot, the voice bot is able to distinguish between different users. Your voice is unique, even for the voice bot!

Main Functions

Upload

Try to upload with pre-recorded audio files.
The file format of WAV is preferred.

Record

Want to interact with the chatbot immediately?
Use the record button to give it a try.


Team Members

                                                                
Dr Serban Ovidiu
Supervisor
Zhiping Huang
Front End Developer
Junfeng Lin
Back End Developer
Zihang Peng
Back End Developer
Xinyi Wu
Project Manager
Baoshun Yan
Front End Developer
Ruiyang Yao
Back End Developer


{% endblock content %}