Effects of linguistic contents on perceptual speaker identification: Comparison of familiar and unknown speaker identifications

Abstract

There are several factors that affect human speaker recognition. In this study, two experiments were conducted in order to see the effects that the stimulus contents and the familiarity to the speakers give to the perception of the speakers. The results showed that: a) stimuli including a nasal were effective for accurate speaker identification; b) coronal nasals were more effective than the labial nasal, and c) the familiarity to the speakers gives a great influence on the performance. The tendencies a) and b) were observed both in familiar and unknown speaker identifications. The results of the acoustical analyses also showed that there were correspondences between the perception of the speaker identity and the cepstral distances among the speakers. The inter-speaker cepstral distances were greater in vowel intervals than in the consonant intervals; especially, notably they were greater in nasals than in orals in the consonant intervals.

Development of Japanese paralinguistic information transmission tests for assessment of hearing-assistance devices utilizing multi-speaker and emotional speech corpora

“…3) Familiarity: Word familiarity has a correlation with the speaker identification score [12]; therefore, in order to avoid this effect, low familiarity score words were selected. Familiarity scores were extracted from "Lexical Properties of Japanese" [13].…”

Perceptual susceptibility to acoustic manipulations in speaker discrimination

“…Other studies have examined the role of higher level aspects such as phonetic content (Amino et al, 2006;Amino and Arai, 2009), fluency in the spoken language (Thompson, 1987;K€ oster and Schiller, 1997;Maheshwari et al, 2008;Perrachione et al, 2011), or speaking rate (Van Lancker et al, 1985b). Studies have also considered the effects of the listening conditions on speaker identification, such as duration of exposure (Compton, 1963;Bricker and Pruzansky, 1966), delay between exposure and identification (Kerstholt et al, 2004), or familiarity with the unknown speaker (Van Lancker and Kreiman, 1987;Yarmey et al, 2001).…”

“…While MFCCs themselves have not been tested in a perceptual context, there is perceptual research to support the importance of spectral envelopes or related information (Coleman, 1973;Remez et al, 1997;Gaudrain et al, 2009;Amino and Arai, 2009).…”

Speaker characteristics that appear in vowel nasalisation and their change over time

“…Most of these studies reported improvements in automatic speaker recognition performances by exploiting nasal sounds or nasal-related parameters as the feature vectors. Some studies also showed that nasal sounds were more advantageous for perceptual speaker recognition than oral sounds [11,12]. Amino and Arai [12] showed that listeners identified speakers more accurately when the presented stimuli contained a nasal consonant than when they did not.…”

“…Some studies also showed that nasal sounds were more advantageous for perceptual speaker recognition than oral sounds [11,12]. Amino and Arai [12] showed that listeners identified speakers more accurately when the presented stimuli contained a nasal consonant than when they did not. This tendency was observed regardless of the listeners' familiarity with the speakers.…”