Automatic Talker Identification Using Optimal Spectral Resolution: Application in noisy environment and telephony

Speech Database

The speech database is extracted from TIMIT (Fisher, Zue, Bernstein & Pallet, 1986) and FTIMIT: TIMIT in which we only preserve the telephonic bandwith (Liu & Fu, 2007) corresponding to the 300-3400 Hz bandwidth (Magrin-Chagnolleau, Wilke, & Bimbot, 1996). There are 37 speakers: 22 males and 15 females. The approximate duration of an utterance is 9 s for the training and 7 s for the test. The recordings are done with a high quality microphone, at 16 bits and with a sampling frequency of 16 kHz.

A second investigation is made in noisy environment (Sayoud, 2003) and with three types of noise (Haque, Togneri & Zaknich, 2006; Hu & Loizou, 2007; Kim & Stern, 2006).

• •

  the Gaussian White Noise: GWN (Paninski, 2006),

• •

  the car noise (Jabloun & Enis Cetin, 1999),

• •

  the babble noise (Elhilali & Shamma, 2008).

These noises are added during the training and test (Sayoud, 2003) at the following rates:

• •

  0 dB,

• •

  6 dB,

• •

  12 dB,

• •

  18 dB,

• •

  24 dB (without noise).