FreeDV 2.0.2 has been released, containing bugfixes for issues discovered after the release of version 2.0.1 as well as Automatic Gain Control for microphone audio and performance improvements. It can be downloaded using the following links: More information about this release can be found on the GitHub release page.| FreeDV
This month, most of my work has been primarily on supporting RADE within the recently-released FlexRadio 8000 series of radios. As I don’t have an 8000 series here, I’ve been doing my development primarily on a Raspberry Pi CM4 connected via Ethernet to my home network (as this is exactly what’s running the software on … Continue reading "Mooneer’s FreeDV Update – September 2025"| FreeDV
This paper is written at a professional technical level and has a description of the BBFM technology including design, derivation of our linearised FM model, training, ASR evaluation results, and the UHF Radio demo. There is a complimentary BBFM web page with demo samples, and Github branch with source code.| FreeDV
This month has mainly been more refinements and bugfixes for the main FreeDV application and the FreeDV Reporter server. Some of these bugfixes and refinements include:| FreeDV
This page is an introduction to our Radio autenocoder (RADE) technology running over bandband FM (BBFM) radios. It has a brief description of the technology and speech samples demonstrating the system. The application is land mobile radio (LMR), for example VHF/UHF walkie talkies, and two-way radios in vehicles for applications such as Amateur Radio, pubic safety, mining, and recreational vehicles.| FreeDV
BBFM Documentation| FreeDV
This is a guest post by Kanda-san, JH0PCF. He and Matsui-san JH0VEQ attended the Ham Fair and discussed FreeDV and RADE. Here is a summary of their fine work at the Ham Fair. Thank you Kanda and Matsui for helping us promote FreeDV – we have noticed that RADE is very popular in Japan so … Continue reading "FreeDV at the JARL Ham Fair 2025"| FreeDV
Peter VK3TPM and Jack VK5KVA made this fascinating video comparing SSB and RADE V1 at 30W down to 1W. More Information on Peter’s blog. This is a really good example of of the low SNR capabilities of RADE and overcoming impulse noise that is making analog HF hard to use for many operators.| FreeDV
Due to stuff happening in my life outside of FreeDV/ham radio, not much progress was made this month. The good news is that version 2.0.1 was released a few weeks ago, which contains a lot of bugfixes reported by users since 2.0.0 was released. Additional bugfixes have gotten into the tree since that release: I … Continue reading "Mooneer’s FreeDV Update – July 2025"| FreeDV
HF RADE Paper Our HF RADE paper “RADE: A Neural Codec for Transmitting Speech over HF Radio Channels” has been peer reviewed and accepted for presentation at WASPAA 2025 in October, so I spent some time with Jean-Marc addressing the reviewers comments. The updated paper can be found on ArXiv. PAPR Issue With our RADE … Continue reading "David July 2025, WASPAA Paper, PAPR, RADE V2 SNR, BBFM OTC Demo"| FreeDV
FreeDV 2.0.1 has been released, containing bugfixes for issues discovered after the release of version 2.0.0. It can be downloaded using the following links: More information about this release can be found on the GitHub release page.| FreeDV
Our Radio Autoencoder (RADE) technology is a new approach to sending speech over HF radio. It combines Machine Learning (ML) with classical DSP to send high quality speech over HF radio at SNRs as low as -2dB. The speech signal has an audio bandwidth of 8kHz, but the RADE V1 signal requires just 1500Hz of RF bandwidth. The Peak to Average Power Ratio (PAPR) is less than 1dB, allowing efficient use of transmitter power amplifiers.| FreeDV