Overview - Spoken Document Retrieval 2000

Proceedings | Results | Runs | Participants

The SDR track fosters research on retrieval methodologies for spoken documents (i.e., recordings of speech). The task in the track is an ad hoc task in which the documents are transcriptions of audio signals.

Track coordinator(s):

• J. Garofolo, National Institute of Standards and Technology (NIST)
• J. Lard, National Institute of Standards and Technology (NIST)
• E. Voorhees, National Institute of Standards and Technology (NIST)

Tasks:

• b1: Baseline Retrieval using medium error recognizer transcripts
• cr: Cross-Recognizer Retrieval using other participants' recognizer transcripts
• r1: Reference Retrieval using human-generated 'perfect' transcripts
• s1: Full SDR using own recognizer
• s2: Full SDR using own secondary recognizer

Track Web Page: https://trec.nist.gov/data/sdr.html

---