The EU project “LISTEN” creates a robust, hands-free speech control interface for smart home systems. During the recent project review meeting, the partners from Germany, Greece, and Italy demonstrated a real-time, matchbox-size, smart-home-specific natural voice interface to web services. “LISTEN” bridges the gap between microphone array networks, signal processing and speech recognition.
Wouldn´t it be convenient to control heating or cooling, lighting, and media anywhere in your home by just using your voice, without any device in your hand? For the elderly and people with disabilities, it would be even more than that: It can provide assistive control of important everyday activities and even save lives, in case of emergencies.
To develop such a novel smart home functionality, speech technology and signal processing experts from Germany, Greece, and Italy collaborate in the EU project “LISTEN” - “Hands-free Voice-enabled Interface to Web Applications for Smart Home Environments”. They are designing a system enabling robust hands-free large-vocabulary voice-based access to Internet applications in smart homes using microphone array networks. http://www.listen-project.eu/
The partners: the Foundation for Research and Technology Hellas (FORTH), Greece (project coordinator), EML European Media Laboratory GmbH, Germany, the RWTH Aachen University, Germany, and Cedat 85, Italy.
“LISTEN” is part of the Marie Skłodowska-Curie Research and Innovation Staff Exchange (RISE) program, in the HORIZON 2020 framework. The four-year project started on June 1, 2015.
In the mid-term project review meeting in Heraklion, Greece, the project partners demonstrated the system in four languages (English, German, Greek, and Italian). To this occasion, the partners already showed important functions of the project, like the multiple language speech recognition and the use of a microphone array, which is a matchbox-size unit with 8 microphones. The EU project officer Alina Suhetzki experienced “LISTEN” by herself. Speaking her commands in English, she switched the lights on and off in a blink. “This was an impressive demonstration”, she said. “A small and smart system that works in real-time with four languages and can also be adapted to further languages.” (See video of the project demonstration at the review meeting in Heraklion https://youtu.be/W_0lh4qk9BI).
“LISTEN” is part of the Marie Sklodowska-Curie Research and Innovation Staff Exchange (RISE) program, in the HORIZON 2020 framework. The four-year project started on June 1, 2015. The partners are: the Foundation for Research and Technology Hellas (FORTH), Greece (project coordinator), the Heidelberg-based EML European Media Laboratory GmbH, Germany, the RWTH Aachen University, Germany, and Cedat 85, Italy.
One goal of the project is to push the boundaries of the current state-of-the-art through basic research activities. Researchers from the partners RWTH Aachen and FORTH, together with colleagues from the University of Paderborn, participated in the 4th CHIME Speech Separation and Recognition Challenge and presented their results at the “International Workshop on Speech Processing in Everyday Environments” in San Francisco in September. The team scored 2nd place in all three different tracks of the challenge, i.e. using 1, 2, or 6 microphones respectively for capturing the speech signals, with 13, 14, and 15 participating teams respectively “We are very proud about the results that clearly indicate the quality of our team, and the potential of LISTEN to develop innovative research and attract the attention of the research community,” says Prof. Athanasios Mouchtaris, LISTEN project coordinator, Associate Professor of Computer Science at the University of Crete and Affiliated Researcher at FORTH.
The “LISTEN” partners are seeking to bridge the gap between the acoustic sensors and the automatic speech recognition research communities. They bring in a lot of expertise from both sides, thus strengthening interdisciplinary research and the exchange of knowledge between universities and companies on a European level.
The Foundation for Research and Technology Hellas (FORTH), Heraklion, Greece, serves as project coordinator. They bring to the project their expertise in acoustic sensor networks and microphone array signal processing. The Heidelberg-based EML European Media Laboratory GmbH (Germany) provides their speech recognition system and refine their tools for the project. The RWTH Aachen University (Germany) speech recognition group brings in its long-time experience and newest technologies in core speech recognition research. Cedat 85 (Italy) brings to “LISTEN” its industrial expertise on building applications and systems that incorporate speech recognition technologies.
For further information, please contact
Dr. Peter Saueressig
EML European Media Laboratory GmbH
Berliner Str. 45
FORTH (Greece) is one of the largest research centers in Greece with well-organized facilities, highly-skilled personnel and a reputation as a top-level research foundation worldwide. In LISTEN, FORTH participates through its Institute of Computer Science (ICS), and more specifically the Signal Processing Laboratory (SPL) which has significant expertise on acoustic sensor networks, sound source localization and beam forming, audio signal modelling and coding, distributed processing, and communications. http://www.ics.forth.gr/
The RWTH Aachen University (Germany) speech recognition group is one of the most prestigious in this area worldwide, with decades of experience in core speech recognition research, including statistical model development, natural language processing, and applications development. http://www-i6.informatik.rwth-aachen.de/
The EML European Media Laboratory GmbH (Germany) is a private IT enterprise established by Klaus Tschira, one of the founders of the SAP AG software company. In accordance with its motto “Experience IT – Intuitive Technology” EML is successfully pursuing research and development in the fields of human-computer interaction and automatic speech processing. http://www.eml.org
Cedat85 (Italy) has a long history of industrial expertise on building specific applications of speech recognition systems, including system integration and evaluation of speech communication systems. http://www.cedat85.com
https://youtu.be/W_0lh4qk9BI video of the project demonstration at the review meeting in Heraklion
Dr. Peter Saueressig | idw - Informationsdienst Wissenschaft
Smart buildings through innovative membrane roofs and façades
31.08.2017 | Fraunhofer-Institut für Organische Elektronik, Elektronenstrahl- und Plasmatechnik FEP
Concrete from wood
05.07.2017 | Schweizerischer Nationalfonds SNF
Pillared graphene would transfer heat better if the theoretical material had a few asymmetric junctions that caused wrinkles, according to Rice University...
The Fraunhofer Institute for Laser Technology ILT and Rapid Shape GmbH are working together to further develop resin-based 3D printing. The new “TwoCure” process requires no support structures and is significantly more efficient and productive than conventional 3D printing techniques for plastic components. Experts from Fraunhofer ILT will be presenting the state-funded joint development that makes use of the interaction of light and cold in forming the components at formnext 2017 from November 14 to 17 in Frankfurt am Main.
Much like stereolithography, one of the best-known processes for printing 3D plastic components works using photolithographic light exposure that causes liquid...
A team of researchers led by Prof. Wolfram Pernice from the Institute of Physics at Münster University has developed a miniature abacus on a microchip which calculates using light signals. With it they are paving the way to the development of new types of computer in which, as in the human brain, the computing and storage functions are combined in one element.
Researchers at the universities of Münster, Exeter and Oxford have developed a miniature “abacus” which can be used for calculating with light signals. With it...
Extremely short electron bunches are key to many new applications including ultrafast electron microscopy and table-top free-electron lasers. A german team of physicists from Rostock University, the Max Born Institute in Berlin, the Ludwig-Maxmilians-Universität Munich, and the Max Planck Institute of Quantum Optics in Garching has now shown how electrons can be accelerated in an extreme and well-controlled way with laser light, while crossing a silver particle of just a few nanometers.
Of particular importance for potential applications is the ability to manipulate the acceleration process, known as a swing-by maneuver from space travel, with...
Cancer cells can reactivate a cellular process that is an essential part of embryonic development. This allows them to leave the primary tumor, penetrate the surrounding tissue and form metastases in peripheral organs. In the journal Nature Communications, researchers from the University of Basel’s Department of Biomedicine provide an insight into the molecular networks that regulate this process.
During an embryo’s development, epithelial cells can break away from the cell cluster, modify their cell type-specific properties, and migrate into other...
30.10.2017 | Event News
23.10.2017 | Event News
17.10.2017 | Event News
03.11.2017 | Physics and Astronomy
03.11.2017 | Earth Sciences
03.11.2017 | Physics and Astronomy