An Approach to Speaker Identification

This presentation will provide standards upon which any attempts to meet the challenge of identifying speakers by voice should be based. It is organized into a model based on (i) application of a rigorous research program validating the system, (ii) an upgrading of the organization of the SI area, and (iii) exploitation of new technology. The second part of the presentation will describe an illustrative speech/voice approach to SI development. This effort is also based on an extensive corpus of research. It is suggested that application of the cited standards, plus the illustrative model, will permit reasonable progress to be made. Finally, a number of procedural recommendations are made; they should enhance the efficacy of the proposed approach.     

长时共振峰分布特征在声纹鉴定中的应用

目的利用长时共振峰分布特征区分不同发音人。方法以汉语普通话为语料,对20位男性发音人和20位女性发音人的前四条共振峰的长时分布情况进行了统计比较分析。结果发现各长时共振峰分布的均值、中位数、众数、峰数、峰度和斜度等参数能够反映出不同发音人的个性特征,稳定性较强。前四条长时共振峰的分布结构比较均匀,由此推测在语料足够长的情况下,所有元音平均后的结果应该是一个类似央元音的＂音＂。结论利用长时共振峰分布特征可以较好地区分不同发音人。     

Bilingualism and the pronunciation of Latvian intonations

For 50 years after World War II, Latvia was incorporated into the former Soviet Union. Although in theory the use of regional languages was not discouraged, in practice knowledge of Russian was obligatory. Since restoration of the country’s independence in 1991, Latvian has again become the official language, and knowledge of Russian is widespread but optional. These political events have created a natural experiment in the possible effects of almost universal bilingualism on a language. In this study, we examine the phonetic characteristics of the Latvian syllable intonations across generations. Native speakers of Latvian, ranging from retirement age to teens, were recorded reading a word list, sentences, and a short narrative. We find that younger speakers who used Latvian only about half of the time showed fading in their pronunciation of the intonations.     

Evaluation of the NITV CVSA

The purpose of this study was to evaluate a commonly used voice stress analyzer, the National Institute of Truth Verification's (NITV) Computer Voice Stress Analyzer (CVSA), using a speech database containing materials recorded (i) in the laboratory, while highly controlled deceptive and shock-induced stress levels were systematically varied, and (ii) during a field procedure. Subjects were 24 each males/females (age range 18-63 years) drawn from a representative population. All held strong views on an issue and were required to make sharply derogatory statements about it. The CVSA system was then evaluated in a double-blind study using three sets of examiners: (i) two UF scientists trained/certified by NITV in CVSA operation, (ii) three experienced NITV operators provided by the manufacturer and (iii) five experimental phoneticians. The results showed that the "true positive" (or hit) rates for all examiners ranged from chance to somewhat higher levels (c. 50-65%) for all conditions and types of materials (e.g., stress vs. unstressed, truth vs. deception). However, the false-positive rate was just as high - often higher. Sensitivity statistics demonstrated that the CVSA system operated at about chance level.     

Stress and Deception in Speech: Evaluating Layered Voice Analysis*

Abstract: This study was designed to evaluate commonly used voice stress analyzers—in this case the layered voice analysis (LVA) system. The research protocol involved the use of a speech database containing materials recorded while highly controlled deception and stress levels were systematically varied. Subjects were 24 each males/females (age range 18–63 years) drawn from a diverse population. All held strong views about some issue; they were required to make intense contradictory statements while believing that they would be heard/seen by peers. The LVA system was then evaluated by means of a double blind study using two types of examiners: a pair of scientists trained and certified by the manufacturer in the proper use of the system and two highly experienced LVA instructors provided by this same firm. The results showed that the “true positive” (or hit) rates for all examiners averaged near chance (42–56%) for all conditions, types of materials (e.g., stress vs. unstressed, truth vs. deception), and examiners (scientists vs. manufacturers). Most importantly, the false positive rate was very high, ranging from 40% to 65%. Sensitivity statistics confirmed that the LVA system operated at about chance levels in the detection of truth, deception, and the presence of high and low vocal stress states.