Live Automatic Speech Recognition (ASR)

Speech Recognition in realtime

The Live ASR technology from Fraunhofer IAIS enables the reliable conversion of spoken information into digital text in real time, even under difficult conditions such as background noise or regional dialects. This technology not only enables natural communication between humans and machines, but also offers an alternative for people with hearing impairments.

The software is already in use, for example, in parliaments for the automatic transcription of speeches. In industrial environments it helps to communicate with machines via voice commands. It offers high reliability in speech recognition, excellent performance in German and English, it is robust against noise, customizable for specific applications and vocabulary, and has word and phoneme output for downstream systems.

Request free demo access

Advantages Fraunhofer Live ASR

On-premise vs. Cloud

You can use Live ASR technology on-premise or in a cloud-based solution.

Customization of live speech recognition

The Live ASR technology can be specialized to your individual use case. Examples are the processing of dialectal speech or the integration of specialized vocabulary. This was successfully implemented for the Saxon parliament, for example.

Data security

Flexibility in server selection allows you to tailor data security to your individual needs and cost structures.

Use case example: Live subtitling in the parliament of the Free State of Saxony

The parliament (Landtag) of the Free State of Saxony uses our speech recognition system for live subtitling of plenary session broadcasts. We were tasked with training the system to recognize a range of specialist legal and political terms as well as the names of politicians.

An additional module automatically inserts punctuation and ensures the text flows naturally and in a structured fashion. Applications requiring a high level of data protection can be installed locally using standard server architecture. Cloud-based speech recognition systems are also equally feasible.