A Database for Research on Detection and Enhancement of Speech Transmitted over HF links
This provides a resource for researchers working on speech processing in HF communications, but it is incremental as it focuses on data collection rather than novel algorithmic advances.
The authors tackled the lack of open data for speech detection and enhancement over HF radio channels by creating a database of time-aligned transmitted and received audio samples from Europe, enabling supervised training of deep learning algorithms, with baseline systems showing performance but no concrete numbers provided.
In this paper we present an open database for the development of detection and enhancement algorithms of speech transmitted over HF radio channels. It consists of audio samples recorded by various receivers at different locations across Europe, all monitoring the same single-sideband modulated transmission from a base station in Paderborn, Germany. Transmitted and received speech signals are precisely time aligned to offer parallel data for supervised training of deep learning based detection and enhancement algorithms. For the task of speech activity detection two exemplary baseline systems are presented, one based on statistical methods employing a multi-stage Wiener filter with minimum statistics noise floor estimation, and the other relying on a deep learning approach.