US 2003/0158732 A1 · Voice barge-in in telephony speech recognition

Abstract

An interactive voice response system is described that supports full duplex data transfer to enable the playing of a voice prompt to a user of telephony system while the system listens for voice barge-in from the user. The system includes a speech detection module that may utilize various criteria such as frame energy magnitude and duration thresholds to detect speech. The system also includes an automatic speech recognition engine. When the automatic speech recognition engine recognizes a segment of speech, a feature extraction module may be used to subtract a prompt echo spectrum, which corresponds to the currently playing voice prompt, from an echo-dirtied speech spectrum recorded by the system. In order to improve spectrum subtraction, an estimation of the time delay between the echo-dirtied speech and the prompt echo may also be performed.

Claims30

Dependent claims

A method, comprising:

detecting an existence of speech in an input signal;
and
removing a prompt echo from the input signal using spectrum subtraction.

Dependencies are inferred from the claim text.

Facts

Application

10/204,034Filed 25 Mar 2003

Published

21 Aug 2003

Term ends

Not estimatedThe source records don’t support an estimate.

Classification9 codes

G01S 13/66
Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose…:…
G01S 13/933
For anti-collision purposes: of aircraft or spacecraft
G10L 15/22
Speech recognition: procedures used during a speech recognition process, e.g. man-machine dialogue
G10L 25/78
Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00: detection of presence or absence of voice signals

Voice barge-in in telephony speech recognition

Life of this patent

Voice barge-in in telephony speech recognition

Life of this patent

Abstract

Claims30