1 These wav files show how Sonic performs at increasing speech rates. All sound 2 sampels are in the public domain. 3 4 sonic.wav 5 This is a sonic 2X sped-up version of a public domain librivox.org recording, from 6 the audiobook "Princess of Mars". 7 8 soundtouch.wav 9 This is the same recording as sonic.wav, but sped up using soundtouch, which 10 uses WSOLA rather than the sonic algorithm. Even at 2X speed up, you should be 11 able to hear the characteristic WSOLA distortion relative to the sonic version. 12 13 talking.wav 14 This is my father talking, using a decent microphone and 44KHz sample rate. 15 16 talking_2x.wav 17 This is his voice sped up by 2X using Sonic. 18 19 espeak_s450.wav 20 Sonic also performs well at increasing the speed of synthesized speech. 21 espeak_s450.wav was generated using 'espeak -s450 -f test1.txt -w 22 espeak_s450.wav'. This is the highest speed currently supported by espeak, 23 though Sonic can speed up espeak to much faster rates. 24 25 espeak_sonic.wav 26 This was generated with 'espeak -f test1.txt -w out.wav; 27 sonic 2.6 out.wav espeak_sonic.wav'. Sonic sped it up 2.6X, which is about the 28 same speed as espeak at -s450. I personally feel that the sonic sped up sample 29 sounds better than espeak at -s450. 30 31 twosineperiods.wav 32 This is just two sine periods, which is too short to hear. However, it's 33 useful for making sure the flush function works correctly. A 2-X speedup should 34 result in one sine period with no distortion. 35
