{"id":3020,"date":"2024-05-22T10:19:35","date_gmt":"2024-05-22T08:19:35","guid":{"rendered":"https:\/\/www.cyberagentur.de\/projects\/audio-forensics-aufo\/"},"modified":"2026-04-28T11:07:20","modified_gmt":"2026-04-28T09:07:20","slug":"aufo","status":"publish","type":"project","link":"https:\/\/www.cyberagentur.de\/en\/programs\/aufo\/","title":{"rendered":"Audio Forensics (AuFo)"},"content":{"rendered":"
    \n
  1. \n Focus:<\/span>\n Secure Society<\/span>\n<\/li>
  2. \n Status:<\/span>\n Project phase<\/span>\n<\/li>\n <\/ol>\n

    Background<\/h3>\n\n

    In the analysis of audio data, the transcription of speech content and the identification of speakers have already been the subject of sufficient research activity. However, the evaluation of meta-information that can be extracted from acoustic signals in addition to spoken language is still a largely unexplored field. In particular, it is not yet known what information can be derived about the environment in which audio data was recorded. This is highly relevant in time-critical application scenarios, such as emergency calls and missing persons cases, or in relation to so-called “Heimlich recordings”. The latter are sound recordings that are made covertly and without the knowledge of other people. They can occur during kidnappings, for example. <\/p>\n\n

    Aim<\/h3>\n\n

    The “Audio Forensics” (AuFo) research program aims to analyze low-quality audio data with regard to the recording location. The aim is to investigate the extent to which partial room acoustic parameters allow a characterization of the recording environment, e.g. with regard to its size, geometry, nature and location (interior\/exterior), in order to ideally be able to make a regional delimitation. In addition to reconstructing the recording location, the aim is to investigate what information can be derived about the recording device, e.g. special characteristics of a smartphone microphone. Depending on the uniqueness of the data, information could also be obtained to uniquely identify, recognize or limit possible sound sources. Ideally, law enforcement authorities will be able to obtain precise location information in time-critical application scenarios, such as kidnapping or missing persons cases, and thus be able to take action. Even initial investigative leads offer considerable added value for law enforcement. <\/p>\n\n

    Disruptive Risk Research<\/h3>\n\n

    In our view, the intended research goal holds great potential for innovation. According to the current state of the art, it is unclear to what extent it is possible to reconstruct the recording location using low-quality audio data. It is also not yet possible to estimate whether the research results will be applicable in the context of criminal prosecution, as forensic methods are to be researched that can be used for legally secure evidence. This represents a major challenge. From a scientific and technical perspective, the program must therefore be considered high-risk research. For this reason, two contractors were selected for the first research phase after extensive examination and intensive rounds of negotiations. <\/p>\n\n