I Sense You by Breath: Speaker Recognition via Breath Biometrics

Over last two decades, Speaker Recognition has primarily been focused on
source
,
system
, and
prosodic
features of the speech. The breath, however, has either been treated as a trivial part of the speech, or considered a noise entity. Our observation reveals that breath is a unique fingerprint of human respiratory system which offers overwhelming results for Speaker Recognition. Moreover, its passive nature, short-duration, fewer occurrences and simple processing results to a light-weight, text-independent and transparent system, which we articulate as BreathID. The breath features are extracted and classified by Mel Frequency Cepstral Coefficients, MFCC, based template matching technique. The verification is performed by a similarity based scheme, whose efficiency competes with classification algorithms. We process a data set collected from 50 users. Our system offers a 0.04 percent False Identification Rate, FIR, for Speaker Identification, and 0.12 percent False Acceptance Rate, FAR, and 0.15 percent False Rejection Rate, FRR, for Speaker Verification. We further evaluate our scheme under various practical modalities, like text in-dependence, replay scenario, users’ motion status (sitting and walking), recording equipment (03 smartphones and 02 microphones), recording period (08 months), and bilingual contents (English and Chinese). Though we use Matlab to formulate a fine-grained approach, we foresee breath biometric as a viable security measure for practical realizations.