Télécom Paris

Doubletalk Detection Using Real Time Recurrent Learning
  • Asif Mohammad, (University of Missouri-Rolla)
  • Jack Stokes, (Microsoft)
  • John Platt, (Micrososft)
  • Arun Surendran, (Microsoft)
  • Steven Grant, (University of Missouri-Rolla)
  • Voice activity detection and double-talk detection
  • Adaptive filtering algorithms and structures for echo and noise control
Get the paper in PDF format
Acrobat Reader (version 5 minimum) is necessary to read this document.

In this paper we present a new system for doubletalk detection that uses multiple signal detectors/discriminators based on recurrent networks. The goal is to build a simple system that learns to combine information from different signal sources to make robust decisions even under changing noise conditions. In this paper we use three detectors - two of these are frequency domain signal detectors, one at the far-end and one at the microphone channel. The third detector determines the relative level of near-end speech vs far-end echo in the microphone signal. The new double-talk detector combines information from all these detectors to make its decision. An important part of this proposed design is that the features used by these detectors can be easily tracked online in the presence of noise. We compare our results with cross-correlation based doubletalk detectors to show its effectiveness.

©2006 Télécom Paris/TSI
Edition : Télécom Paris -- 2006