Speaker recognition using lower formants

Abstract

Speaker recognition is the areu ofspeech teechnoloa, which atfem@r to identfy the speukeu. There are hvn distinct uppuuaches in fhis domain. One is bused on hlind DSP prnceming where we deal wifh the signal regardless of its content. The other is phonetic based where indviihal phonemic unity are identij'ied processed and niafched on (he basis of cevtuin,fiatures. Our vestarch is relafed lo the second approach and we have iried io ideiifjfi high level phonemic fearuves Iike sfyle etc. from the pocessing of lower formants. We hove lried to process these ,for.mnnls on transition boundaries and dleivp[ed to demonstrate that each person has a speciJii. pUtl~r7 oJrisc andxall in the tiansirion region. Ow bosic hyputhesis is: The tiwrisiliun gf ,formunh ut the coirsonanf-vuwel bozincfurir.r is corrirolled by the brain and it conlains a speciJic signatirt-e ut' the speuker. Expei-itnents have shown thut our method has a success rate of' 90%. Moreover., the system gives desiruble resulis, eveti in a noisy environment due to the choice o j lower formants.

Improving Speaker Recognition by Biometric Voice Deconstruction

“…On the other hand, spectral level has been extensively used in speaker recognition systems for feature extraction. Typical methods in this spectral level are as follows: Short-time spectrum (no matter if we use the exact representation or its approximation by filter banks) (Xiang and Berger, 2003 ; Seddik et al, 2004 ; Burget et al, 2007 ), predictor coefficients [based on a linear model of speech production: (Park et al, 2006 )], formant frequencies and bandwidth [defined as the resonance frequencies of the vocal tract: (Fatima et al, 2004 )], or even the formant trajectories (Tanabian et al, 2005 ).…”

Vowel-category based Short Utterance Speaker Recognition

“…A study of formant contours at consonant-vowel boundary shows that a speaker can be identified using the consonant to vowel transition information. The speaker information at the transition was named the "speaker-style" [11]. The biannual National Institute of Standards and Technology (NIST) Speaker Recognition Evaluation (SRE) also presents the optional test of 10-second evaluation [12].…”

“…The length of utterance in most of these cases is around 10 seconds. Other than [10] and [11], most of the researches make use of utterances no less than 2 seconds. In light of these researches, we strive to find the usefulness of phonemes in speaker recognition using utterance length equal to the size of a long vowel.…”