Method of detecting speech and speech detector for low signal-to-noise ratios
AssigneeGN Hearing A/S
InventorsRob Anton Jurjen De Vries, Tobias Piechowiak
Life of this patent
Estimating the term…
Abstract
The present disclosure relates in a first aspect to a method of detecting speech of incoming sound at a portable communication device. A microphone signal is divided into a plurality of separate frequency band signals from which respective power envelope signals are derived. Onsets of voiced speech of a first frequency band signal are determined based on a first stationary noise power signal and a first clean power signal and onsets of unvoiced speech in a second frequency band signal are determined based on a second stationary noise power signal and second clean power signal.
Claims32
A method performed by a communication device, the method comprising:
- generating a microphone signal by the communication device based on sound;
- dividing the microphone signal into a plurality of frequency band signals comprising a first frequency band signal in a first frequency band, and a second frequency band signal in a second frequency band;
- determining a first stationary noise power signal associated with the first frequency band;
- determining a first clean power signal associated with the first frequency band;
- determining a second stationary noise power signal associated with the second frequency band;
- determining a second clean power signal associated with the second frequency band;
- determining an onset of voiced speech based on the first stationary noise power signal and the first clean power signal;
- determining an onset of unvoiced speech based on the second stationary noise power signal and the second clean power signal;
- and
- obtaining a speech flag or marker;
- adjusting a signal processing parameter based on the speech flag or the marker;
- and
- providing an acoustic signal reception by a user, wherein the acoustic signal is generated by the communication device based on the signal processing parameter.
A speech detector configured to obtain a plurality of separate frequency band signals based on a microphone signal, the frequency band signals comprising a first frequency band signal in a first frequency band, and a second frequency band signal in a second frequency band, the speech detector comprising:
- a processing unit configured to:
- determine a first stationary noise power signal associated with the first frequency band;
- determine a first clean power signal associated with the first frequency band;
- determine a second stationary noise power signal associated with the second frequency band;
- determine a second clean power signal associated with the second frequency band;
- determine an onset of voiced speech that is associated with the first frequency band based on the first stationary noise power signal and the first clean power signal;
- and
- determine an onset of unvoiced speech that is associated with the second frequency band based on the second stationary noise power signal and the second clean power signal;
- wherein the speech detector is configured to provide a speech flag or marker for a communication device, wherein the communication device is configured to adjust a signal processing parameter based on the speech flag or the marker, and to provide an acoustic signal for transmission into an ear canal of a user, wherein the communication device is configured to generate the acoustic signal based on the signal processing parameter.
Dependencies are inferred from the claim text.