CHAPTER 14 AUDIO DEMONSTRATIONS: SPEAKER RECOGNTION

-------------------------------------------------------------------
Audio Demo 14.1: Some prosodic and excitation 
	         modifications used in speaker recognition 
	         experiments from modified speech
		   - modifications performed with the 
		     sinusoidal analysis/synthesis 
		     system of Section 9.5.2

Prosody
-------
bago_seg1.8k              	Original 
bago_seg1.pitMono.8k      	Monotone pitch 
bago_seg1.tsmB04Y.8k    	Pitch-raised and time-scaled expanded

Excitation
----------
sc_seg.8k                	Original 
sc_seg.whispered.8k    		Whispered (more accurately described 
			          as "raspy")


-------------------------------------------------------------------
Audio Demo 14.2: Glottal flow derivative (GFD) waveforms used in 
	         speaker recognition experiments
		   - Estimation performed with methods
		     described in Chapter 5.8.2


ln.roy.10k              	Original 
ln.roy.GPTimes.10k    		Glottal onset times (large impulses)/
				  closed-phase region (within small impulses)
ln.roy.GFD.10k          	Synthesized glottal flow derivative estimate 
ln.roy.LF_MGFD.10k    		Synthesized LF-modeled glottal 
				  flow derivative estimate

figure_ln.roy.GFD   		Spectrogram comparison of (top to bottom) 
  			          a: ln.roy.10k 
			          b: ln.roy.GFD.10k
			          c: ln.roy.LF_MGFD.10k

Notes:
	- The GFDs have roughly flat spectra except for 
	  1st-formant resdiual and spectral tilt, as predicted


-------------------------------------------------------------------
Audio Demo 14.3: Nonlinear transformation of electret to carbon-button 
	         handset 
		   - Using mapping design technique of Section 14.5.2

mfgk0_el1.8k [*]   		Speech through electret handset              
mfgk0_cb3.8k    		Speech through carbon-button handset
mfgk0_el12cb3_03Ef02.8k    	Result of electret-to-carbon-button mapping

[*] Speech samples are from the HTIMIT database.


-------------------------------------------------------------------