Hisanori Makinae

Effects of the Phonological Contents and Transmission Channels on Forensic Speaker Recognition

This chapter introduces experiments on speaker recognition where we focus on two of the factors that affect speaker recognition accuracy: phonological contents of the speech materials used for identifying speakers and the transmission channel difference in automatic speaker verification. Through the experiments, we show that nasal sounds are effective for forensic speaker recognition despite the differences in speaker sets and recording channels. Also we show that performance degradation by the channel difference, in this study air- and bone-conduction, can be improved by devising normalisation methods and acoustic parameters.

Historical and Procedural Overview of Forensic Speaker Recognition as a Science

Forensic phonetics and acoustics are nowadays widely used regarding police and legal use of acoustic samples. Among many tasks included in this area, forensic speaker recognition is considered as one of the most complex problems. Forensic speaker recognition, sometimes called forensic speaker comparison, is a process for making judgments on whether or not two speech samples are from the same speaker. This chapter introduces the historical backgrounds of forensic speaker recognition including “voiceprint” controversy, human-based visual and auditory forensic speaker recognition, and automatic forensic speaker recognition. Procedural considerations in forensic speaker recognition processes and factors that affect recognition performances are also presented. Finally, we will give a summary of the progress and developments made in the forensic automatic speaker recognition.

Speaker Verification in Realistic Noisy Environment in Forensic Science

In forensic voice telephony speaker verification, we may be requested to identify a speaker in a very noisy environment, unlike the conditions in general research. In a noisy environment, we process speech first by clarifying it. However, the previous study of speaker verification from clarified speech did not yield satisfactory results. In this study, we experimented on speaker verification with clarification of speech in a noisy environment, and we examined the relationship between improving acoustic quality and speaker verification results. Moreover, experiments with realistic noise such as a crime prevention alarm and power supply noise was conducted, and speaker verification accuracy in a realistic environment was examined. We confirmed the validity of speaker verification with clarification of speech in a realistic noisy environment.

Fundamental frequency estimation combining air-conducted speech with bone-conducted speech in noisy environment

Air-conducted speech is currently used for fundamental frequency extraction in noisy environment. However, the results are severely affected by noise. In this paper, additionally bone-conducted speech is combined with air-conducted speech and a novel pitch extraction method is derived. Experiments indicate that the proposed method provides an accurate estimate of fundamental frequency of speech in highly noisy environment.

A preliminary acoustic analysis of three-dimensional shape of the human nasal cavity and paranasal sinuses extracted from cone-beam CT

The shape of the nasal cavity and paranasal sinuses is complex and varies between individuals. Because the shape is almost stable during speech, the acoustic properties could constantly provide speaker specific information to speech sounds, that is, speaker individuality. In this preliminary analysis, the shape was extracted from cone-beam CT data for a subject using a machine learning technique and its acoustic properties were examined using finite-difference time-domain simulation. The transfer function from the glottis to the nostrils was calculated and the distribution pattern of the pressure anti-nodes was visualized at frequencies of major spectral peaks and dips. In addition, transfer functions were calculated when each of the paranasal sinuses other than the ethmoidal ones was occluded to identify which sinus caused which dip. As a result, the longitudinal resonance in the right or left half of the nasal cavity generated each peak, while the transverse resonance in the pharyngeal cavity caused the...