CCW 2020: Fraunhofer IDMT presents solutions for personal sound settings and speech recognition on the telephone
From 2-4 March 2020, the Division Hearing, Speech and Audio Technology of the Fraunhofer Institute for Digital Media Technology IDMT in Oldenburg will be at Call Center World (CCW) in Berlin and demonstrate how telephone workstations can be made more efficient and pleasant through intelligent solutions. On IDMT’s stand (C11, Hall 2), CCW visitors can find out about personal hearing systems that dynamically adapt the sound of telephone calls to personal preferences. The institute’s experts will also show the added value of their automatic speech recognition technology for telephone workstations.
Staff at telephone workstations are permanently confronted in their everyday work with different acoustic effects. Incoming calls vary in sound quality and volume level. Background noise in the office also has an impact on the intelligibility of a telephone conversation. As a consequence, the call centre agent is obliged to adjust constantly to new conditions with each conversation or can sometimes scarcely even hear or understand the other person, which over time can be very strenuous.
Better intelligibility at the push of a button
The Fraunhofer IDMT in Oldenburg has developed special algorithms for use in telephone workstations that adapt the sound of telephone calls to individual preferences. »We give call centre staff a sound quality that is as consistent as possible throughout their entire working day,« explains Christian Rollwage, Head of Audio Signal Enhancement at the Fraunhofer IDMT in Oldenburg. »This makes the telephone workstation a personal comfort zone with optimum conditions for better speech intelligibility and reduced hearing effort.«
The experts from the Fraunhofer IDMT in Oldenburg will showcase a plug-and-play device at CCW 2020 that can be easily combined with analogue telephones or softphones. The device is an example of how the algorithms developed especially for telephony can be applied in practice and was developed in cooperation with call centres in line with their specific requirements. Users can select what are known as »presets« at the push of a button. These dynamically adjust the sound of incoming calls to individual hearing preferences and at the same time automatically reduce distracting and ambient noise. Another special feature is the dynamic adjustment of sound and volume level depending on the background noise in the workplace.
Speech recognition as the basis for better customer service
Where customer communication mainly takes place on the telephone, automatic speech recognition can generate considerable added value. Digital voice assistants respond to customer enquiries. Documentation tasks can be accomplished simply via speech-to-text and the text produced in this way stays searchable for different tasks. Keywords in telephone calls are recognized, helping the agent to offer the customer the best possible service and to conduct the conversation confidently.
At CCW, the Fraunhofer IDMT in Oldenburg will present its speech recognition systems for integration in a wide variety of business solutions. The extensive customization and integration support offered by the “voice enabler” from Oldenburg can be highlighted as particular added value. This makes it possible to adapt the speech-to-text systems individually, for example, to the required vocabulary. Thanks to low resource requirements, good scalability and offline operation, local use on a chosen system or the corporate cloud in compliance with the GDPR and the highest data privacy standards is easily possible.
Meet the developers from the Fraunhofer Institute for Digital Media Technology IDMT, Hearing, Speech and Audio Technology Division (HSA), at CCW 2020 from 2 to 4 March 2020, Hall 2, Stand C11.
The Hearing, Speech and Audio Technology Division (HSA) at the Fraunhofer Institute for Digital Media Technology IDMT in Oldenburg
The objective of the Hearing, Speech and Audio Technology Division (HSA) of the Fraunhofer Institute for Digital Media Technology IDMT is to transpose scientific findings related to hearing perception and human-technology interaction into technological applications. Its applied research priorities are the enhancement of sound quality and speech intelligibility, personalized audio reproduction and acoustic speech recognition and event detection with the help of artificial intelligence. A further focus is the use of mobile neurotechnologies, which facilitate the recording of brain activity and utilization of the resulting data outside the laboratory too. Application fields include consumer electronics, transport, the automotive sector, industrial production, security, telecommunications and healthcare. Through scientific partnerships, Fraunhofer IDMT-HSA has close links with the Carl von Ossietzky University of Oldenburg, Jade University and other institutions engaged in hearing research in Oldenburg. Fraunhofer IDMT-HSA is a partner in the »Hearing4all« Cluster of Excellence. The Division Hearing Speech and Audio Technology is being funded by the Ministry of Science and Culture and the Volkswagen Foundation for its transfer to a separate institute for Hearing Speech and Neurotechnologie in the Lower Saxony "Vorab" programme.