Fixing Voice Breakups with Deep Learning

At 2Hz we are continuously rethinking traditional approaches to known problems in Voice processing and disrupting them by applying deep learning.

Our last article has discussed the problem of bandwidth expansion in voice audio.

This time it’s PLC’s turn.

PLC (Packet Loss Concealment) is a well known problem in voice communications. It’s also known to every telecommunication user in the world. Everyone, literally everyone who used VoIP Apps or Cellular Phone has experienced “chopped voice”. When network conditions are bad our voice is cutting off and sounds annoying and funny. Early Skype users remember this very well. We sound like “he e ey how aaaaaare yoo ooo”?

In this article we demonstrate how our Deep Neural Network (DNN) powered PLC algorithm (krispNet-PLC) compares to existing state of the art PLC technologies.

The full article can be found here:

https://2hz.ai/blog/fixing-voice-breakups/index.html

When AI meets Human Voice

This is the first blog post about what we do at 2Hz and I’m super excited.

At 2Hz we are building tools and APIs for Voice Manipulation.

While Voice is so fundamental in Humans’ life, we believe there are not enough tooling and technology which would enable using our Voice to its maximum extend.

We are still in early stages of Voice communications. Telecommunications enable voice to be travelled thousands of miles per second, speech to text technologies enable computers to understand our intents. And this is all magical.

However we believe that the next level of disruption in Voice technologies will happen when there is a simple tooling which allows understanding, differentiating, enhancing and manipulating Human Voices.

Imagine multiple people speaking to a machine in a busy and noisy street. Now imagine that the machine is able to separately understand what each of the people is saying (or maybe yelling), their average age, gender and mood, is able to distinguish every sound in the background and answer back to everyone in the manner necessary for it.

There are many such examples that explain what Human Voice Manipulation means. We will share these over time. The important message here is that once we understand what a human voice is we can create incredible new experiences for people.

When AI meets Human Voice beautiful things will happen.

More to come…