Graceful degradation of speech recognition performance over packet-erasure networks

Constantinos Boulis, Mari Ostendorf, Eve A. Riskin, Scott Otterson

Research output: Contribution to journalArticlepeer-review

43 Scopus citations

Abstract

This paper explores packet loss recovery for automatic speech recognition (ASR) in spoken dialog systems, assuming an architecture in which a lightweight client communicates with a remote ASR server. Speech is transmitted with source and channel codes optimized for the ASR application, i.e., to minimize word error rate. Unequal amounts of forward error correction, depending on the data's effect on ASR performance, are assigned to protect against packet loss. Experiments with simulated packet loss in a range of loss conditions are conducted on the DARPA Communicator (air travel information) task. Results show that the approach provides robust ASR performance which degrades gracefully as packet loss rates increase. Transmitting at 5.2 Kbps with up to 200 ms added delay, leads to only a 7% relative degradation in word error rate even under extremely adverse network conditions.

Original languageEnglish
Pages (from-to)580-590
Number of pages11
JournalIEEE Transactions on Speech and Audio Processing
Volume10
Issue number8
DOIs
StatePublished - Nov 2002

Keywords

  • Bit allocation
  • Forward error correction
  • Packet loss
  • Speech recognition
  • Unequal loss protection

Fingerprint

Dive into the research topics of 'Graceful degradation of speech recognition performance over packet-erasure networks'. Together they form a unique fingerprint.

Cite this