Speech Is Golden - On ASR at the Service of the Danish Public Sector
published: Nov. 7, 2016, recorded: September 2016, views: 1234
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
In this talk I’ll present the introduction of automatic speech recognition in the Danish municipalities. Ready to begin to adopt ASR, most municipalities remain nervous following a long series of bad business cases in the recent past. Complaints are voiced over costly licences and low service levels, typical effects of a de facto monopoly on the supply side. As a counteract, DanCAST (Danish Center for Applied Speech Technology) established a consortium three years ago involving more than half of the Danish municipalities, a number of SMEs, NGOs, and other organizations, together constituting a body strong enough to formulate a number of requirements to be met by suppliers and tendering material allowing fair competition. The consortium has also formulated guidelines for the collection and unrestricted sharing of a corpus of transcribed speech samples and text materials necessary (and sufficient) for developing professional ASR applications. The corpus is steadily growing, paving the way for fair competition among large and small ASR suppliers to the public sectors. In the talk I’ll break down our motivations, events and actions, and comment on the benefits of national-scale cooperation in ASR development for small language areas.
Download slides: jtdh2016_henrichsen_danish_public_sector_01.pdf (1.2 MB)
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !