Please note that JavaScript and style sheet are used in this website,
Due to unadaptability of the style sheet with the browser used in your computer, pages may not look as original.
Even in such a case, however, the contents can be used safely.
- NEC's R&D
- R & D Domains
- Cloud Research
- Datamining
- Natural Language Processing
- Secure System
- Multimedia Communication
- Cloud service Life Cycle Management
- Model base SI
- Human Interface
- Real World Interfaces
- SDN (Software-Defined Networking)
- Big Data Processing
- Video-image recognition/identification technology
- Speech recognition
- Media integration middleware
- Green Innovation Research
- Cloud Research
- Global R & D
- Press Release
- Innovative Engine
- Awards
- Access
Actual environment conversation and speech recognition
Real world speech recognition
To understand the events that take place in the real world, speech and sound information captured by the ears is also important. Speech in particular is one of the easiest and most efficient means of humans for communicating deep meaning to one another. By recognizing and understanding speech, the intellectual activities of humans can be taken in and used by the IT world.
The Information and Media Processing Laboratories are engaged in research and development of speech recognition technology that recognizes the words that people speak naturally to one another. The creation of this technology will make it possible to automatically prepare records of parliamentary meetings and conferences, and to extract useful information from the voices of customers who contact call centers. We are also conducting research and development of noise-tolerant speech recognition technology, which recognizes speech even in extremely noisy locations. This technology will make it possible to operate terminals by voice and input work results by speaking them, even in high-noise environments such as factories. We have also created an automated interpreting function that supports communication with foreigners by combining speech recognition, machine translation, and speech synthesis in a small terminal.
In the future, by developing technology that supports more informal speech and speech in even noisier environments, we will make it possible to recognize and understand speech in all kinds of environments and situations, creating solutions that render human activities more efficient and more dynamic by making use of the information thus obtained.
