In everyday life, people recognise speech under a wide range of conditions that are "non-optimal" relative to the controlled conditions in laboratory experiments. Traditional research methods can only deal with the effects of individual "adverse" conditions. This has contributed to the fragmentation of speech communication research into numerous sub-disciplines that have little interaction. While each type of adversity can have important consequences on its own, it is often the combination of conditions that conspire to create serious communication problems, especially for elderly and hearing impaired persons.

Starting Jan 2012, the FP7 Marie Curie Initial Training Network Investigating Speech Processing In Realistic Environments (INSPIRE) provides research opportunities for 13 PhD students (Early Stage Researchers - ESRs) and 3 postdocs (Experienced Researchers - ERs) to study speech communication in real-world conditions. The network consists of 10 European research institutes and 7 associated partners (5 companies and 2 academic hospitals). The senior researchers in the network are academics in computer science, engineering, psychology, linguistics, hearing science, as well as R&D scientists from leading businesses in acoustics and hearing instruments, and ENT specialists.

This project has received funding from the European Union’s Seventh Framework Programme for research, technological development and demonstration under grant agreement no FP7-PEOPLE-2011-290000.

The INSPIRE project website: www.inspire-itn.eu/

Items in this Collection

  • Repeated Harvard Sentence Prompts corpus version 0.5 

    Henter, Gustav Eje; Merritt, Thomas; Shannon, Matt; Mayo, Catherine; King, Simon (University of Edinburgh, Centre for Speech Technology Research; Cambridge University Engineering Department, 2014-06-19)
    Studio recording of female native British English talker producing three sets of Harvard sentences (thirty prompts), each prompt repeated forty times. Available both as unprocessed 96 kHz recordings and standardised 16 kHz files.