Breathing signal-dependent speech processing of an audio signal

An apparatus comprising:

• an input circuit,
• wherein the input circuit is arranged to receive an audio signal,
• wherein the audio signal comprises a speech audio component for a speaker;
• a segmenter circuit,
• wherein the segmenter circuit is arranged to generate a plurality of segments of the audio signal,
• wherein each segment of the plurality of segments have a segment duration,
• wherein consecutive segments have an intersegment duration,
• wherein the intersegment duration is a time between consecutive segments of the plurality of segments,
• wherein the segment duration is greater than an intersegment duration so that the consecutive segments of the plurality of segments overlap;
• a first generator circuit,
• wherein the first generator circuit is arranged to generate a fragment of a breathing waveform signal from the each segment of the plurality of segments,
• wherein at least a portion of the fragments have a fragment duration greater than the intersegment duration;
• a second generator circuit,
• wherein the second generator circuit is arranged to generate the breathing waveform signal by combining the fragments of the breathing waveform signal,
• wherein the second generator circuit is arranged to combine at least a portion of the fragments by applying a weighted combination to samples of different fragments for the same time instant,
• wherein weights of the weighted combination is determined from a fragment window function;
• and
• a speech processor circuit,
• wherein the speech processor circuit is arranged to apply a speech processing to the audio signal,
• wherein the speech processing is based on the breathing waveform signal.