A software development company has contacted you to create a speech recognition system to

integrate in a Python project they are developing. In particular, the project consists of an airport

virtual assistant.

You have to build a prototype of the application $($exercise $4)$ that should meet the following

requirements:

$1.$ The application must be written in Python.

$2.$ Your client prefers to host the ASR software package in the application to avoid slow$-$down

or interruptions to the system in the event of issues with the internet connection. In

particular, they want you to base the speech recognition system on the Mozilla DeepSpeech

software package.

$3.$ The application must be capable of language$-$selection, at the very least compatible with the

following languages: English, Italian and Spanish $($see document Ex$4\_$models.pdf$).$

$4.$ The airport virtual assistant will be installed in an environment that can be extremely noisy.

So$,$ the speech recognition system should be configured to be able to handle this situation.

Your client gives you freedom for implementing any solution $($for example, to configure in

python a gain$/$amplification$,$ low pass filter, or some other audio filter to improve the error

rate$).$

$5.$ The company has prepared a set of audio files with which you can evaluate the system. For

this evaluation, you will test how well it recognises several phrases in each language. You

also have to record and evaluate two short sentences $($your$\_$sentence$1.$wav and

your$\_$sentence$2.$wav$).$ Feel free to prepare your own sentences.