Audio Samples from "Spatial Voice Conversion: Voice Conversion Preserving Spatial Information and Non-target Signals"

Voice Conversion (VC) samples

• Source: The source speech for spatial voice conversion. Stereo recordings of two speakers' voices.
• Target (Ideal): The desired speech with spatial voice conversion. Referred to as "Ideal" in the paper.
• Converted (Inverse): The output of spatial voice conversion using method described as "Inverse" in the paper.
• Converted (Steering): The output of spatial voice conversion using method described as "Steering" in the paper.

Stereo audio samples

	Source	Target (Ideal)	Converted (Inverse)	Converted (Steering)
Sample 1 (target: male)
Sample 2 (target: male)
Sample 3 (target: female)
Sample 4 (target: female)

Monaural audio samples

Left channel (target of projection back)

	Source	Target (Ideal)	Converted (Inverse)	Converted (Steering)
Sample 1 (target: male)
Sample 2 (target: male)
Sample 3 (target: female)
Sample 4 (target: female)

Right channel

	Source	Target (Ideal)	Converted (Inverse)	Converted (Steering)
Sample 1 (target: male)
Sample 2 (target: male)
Sample 3 (target: female)
Sample 4 (target: female)