Blog

Machine learning on edge devices

Top mistakes when creating audio datasets for machine learning

Creating an audio dataset for machine learning can be a complex and time-consuming task. Unfortunately, many people make mistakes when creating these datasets, which can lead to poor performance of machine learning models. Here, we will discuss some of the common mistakes made when creating audio datasets for machine learning and how to avoid them.…
Read more

Avoiding common pitfalls when deploying machine learning models to edge devices

Bringing machine learning models to production can be a challenging process, and there are several mistakes that can be made along the way. Here are three of the biggest mistakes to avoid, as well as solutions to help you overcome these obstacles. Not meeting CPU/Memory requirements One of the biggest mistakes when bringing machine learning…
Read more

Machine learning on Embedded Systems

Leaving the baby shoes When we think of machine learning people often have gigantic models on cloud servers in their mind. But with ongoing improvements more and more applications become possible at the edge and here efficiency is king. Many methods have been suggested for making neural networks more efficient. Some of them are on…
Read more

Nyumaya wake-word now on ESP32S3

As the world continues to move towards a more connected and digitized future, the use of voice interfaces has become increasingly popular. This technology allows users to interact with devices in a natural and intuitive way, making tasks and processes more efficient and user-friendly. At Nyumaya, we are excited to announce that we now offer…
Read more

Audio Recognition Web Demo

In today’s fast-paced business world, time is a valuable commodity. Nobody wants to waste it on tedious and time-consuming tasks, especially when it comes to evaluating new software. That’s why we made it easy for users to try out our product without any hassle. In the past, many companies required users to create an account…
Read more

Voice as an Interface

Using voice as an interface has been terrible in the past, and felt more like a gamble than accurate control. But with recent improvements in speech recognition and natural language understanding, smart assistants conquered our homes. But can a voice interface actually be useful and more than just a fun toy to show off? Why…
Read more

The hidden value of audio data

Use machine learning to uncover the hidden value of audio data

Audio contains lots of valuable data Audio is one of the five human senses and carries surprisingly much information. Close your eyes and listen to some sounds nearby. Chances are you can get a pretty good overview of what’s going on around you. You can hear cars passing by and count them. You can estimate…
Read more

Wake-word on Pi Zero

Why do I need wake-word detection

The wake-word is a gateway to your Speech Interface The use of a wake-word or hot-word in a digital voice interface serves two important purposes. First, it helps to limit the amount of audio that needs to be processed for speech recognition. This is important because transcribing speech to text can be a challenging task,…
Read more