Audio Demonstrations
Publication:
Yousefian, N. and Loizou, P. (2012). "A Dual-Microphone Algorithm that can Cope with Competing-Talker Scenarios," submitted to IEEE Trans. Audio, Speech, Language Processing,
SNRs are set at the sound sources before convolving the input signals with HRTFs (T60 = 80 ms).
Example Sentence 1 (One noise source)
|
Method / Masker at 90 degree (SNR = 0 dB ) |
Speech-shaped noise |
Multi-talker babble |
Female competing talker |
|
Simulated Software Directional Mic. |
|||
|
Processed via SNR-Coherence |
Example Sentence 2 (Two noise source)
|
Method / First masker at 90 and the second at 180 degree (SNR = 0 dB ) |
Multi-talker babble and speech-shaped noise |
Female competing talker and male competing talker |
|
Simulated Software Directional Mic. |
||
|
Processed via SNR-Coherence |
Example Sentence 3 (Two noise sources)
|
Method / First masker at 90 and the second at 270 degree (SNR = 0 dB ) |
Multi-talker babble and speech-shaped noise |
Female competing talker and male competing talker |
|
Simulated Software Directional Mic. |
||
|
Processed via SNR-Coherence |