Posts tagged Python

Whisper based speech recognition server

In the last blog post: Token authenticated aiohttp server, an authenticated aiohttp server was introduced. In this post, we build on top of the previous posts, to create an Automatic Speech Recognition (ASR) authenticated server, that uses the newly introduced whisper by OpenAI.

Read more ...

Token authenticated aiohttp server

In the previous blog post, a simple aiohttp server was introduced. In the following post we improve the previous server by introducing a simple token authentication mechanism.

Read more ...

Basic aiohttp server

When it comes to deploying an application on a server online, a crucial aspect is its response time since no user wants to wait long for a response. Hence, optimizations and asynchronous processing are the way to go. within this context, aiohttp is a python library that helps implementing asynchronous HTTP Client/Server. The following blog is one of a series of four that will introduce a server implementation, followed by a token based authentication and some stress testing.

Read more ...

Root mean square normalization in Python

Audio normalization is a fundamental audio processing technique that consists of applying a constant amount of gain to an audio in order to bring its amplitude to a target level. A commonly used normalization technique is the Root Mean Square (RMS) normalization. This blog post introduces RMS normalization and provides a Python implementation of it.

Read more ...

Introducing urlstechie and its urls checking tools

Continuous testing is a vital part of any healthy software development process. Urls must always be tested and broken links must be fixed to guarantee a high quality product. Unfortunately, this is not always trivial and can be tedious. Moreover, most tools available out there cannot handle in-code urls and lack many other needed features. A while back, I ran across this particular Problem and I quickly saw the great automation opportunity this was, and how can Python and Regex help me solve this. This was the start of the urlchecker-action ... from there and with the amazing @vsoch joining, the tools expanded and this was the start of the urlstechie organization.

Read more ...

How to pipe an FFmpeg output and pass it to a Python variable?

When writing code, the key optimization points are speed and efficiency. I often face this dilemma when using FFmpeg with Python. For example: when I need to convert an mp3 to a wave file and then do some processing to it in Python. The simple way to do this, is by using FFmpeg to convert the mp3 input to a wave, then read the wave in Python and do process it. Although this works, but clearly it is neither optimal nor the fastest solution. In this blog post, I will present an improved solution to this inconvenience by piping the output of FFmpeg to Python and directly pass it to a numpy variable.

Read more ...

Spectral leakage and windowing

Windowing is an important part of almost any signal processing system, that helps remove/ reduce spectral leakage when processing a non-periodic signal. This blog post provides a small overview of what is spectral usage, when does it occur and how to use windowing to suppress it.

Read more ...

Naive voice activity detection using short time energy

An important part of speech/speaker recognition tasks is distinction of voiced segments from silent ones. This helps -for example- align phonemes with their associated voiced segments and avoid any extra information related to silence/ noise that would degrade the system's accuracy. This problem is known as Voice Activity Detection (VAD). This blog aims to introduce voice activity detection and present simple short time energy based VAD implementation.

Read more ...

Signal framing

When it comes to non-stationary signals, spectral features in short parts/ sequences are of great use. Therefore, decomposing the signal into multiple ranges is the way to go about this type of features extraction. This technique is known as frame blocking or framing. The following blog explains why do we need framing and how to do it in python.

Read more ...

Diabetes detection using machine learning (part II)

In this 2nd post on detecting diabetes with the help of machine learning and using the Pima Indian diabetic database (PIDD) 1, we will dig into testing various classifiers and evaluating their performances. We will also examine the performance improvements by the data transformations explained in the previous post.

Read more ...

Diabetes detection using machine learning (part I)

Diabetes is one of the most serious health challenges today. The publicly available Pima Indian diabetic database (PIDD) have become a popular approach for testing the efficiency of machine learning algorithms 1. Within this context, this blog post is part of 2 posts providing an in depth introduction to diabetes detection using various machine learning approaches. In this first post in particular, we focus on exploring the data at hand and preparing it for machine learning related processing.

Read more ...

Voice based gender recognition using Gaussian mixture models

The aforementioned implementation, uses The Free ST American English Corpus data-set (SLR45), which is a free American English corpus by Surfingtech, containing utterances from 10 speakers (5 females and 5 males).

Read more ...