Speaker idiosyncratic variability of intensity across syllables
نویسندگان
چکیده
This study explored speaker idiosyncrasy by measuring the syllabic intensity variability in the speech signal. Sixteen speakers of the TEVOID corpus, each producing 256 read sentences, were analyzed. Characteristics of intensity variability (average or peak) between syllables were measured either holistically (standard deviation of intensity changes between syllables) or locally (pairwise variability indices of intensity changes between syllables). The results indicated significant effects of the speakers in all the metrics, suggesting a potential application of the methods for speaker recognition, and in particular for forensic speaker comparison.
منابع مشابه
Relationship between acoustic measures and speech naturalness ratings in Parkinson's disease: A within-speaker approach.
This study investigated the acoustic basis of across-utterance, within-speaker variation in speech naturalness for four speakers with dysarthria secondary to Parkinson's disease (PD). Speakers read sentences and produced spontaneous speech. Acoustic measures of fundamental frequency, phrase-final syllable lengthening, intensity and speech rate were obtained. A group of listeners judged speech n...
متن کاملBetween-speaker variability in temporal organizations of intensity contours.
Intensity contours of speech signals were sub-divided into positive and negative dynamics. Positive dynamics were defined as the speed of increases in intensity from amplitude troughs to subsequent peaks, and negative dynamics as the speed of decreases in intensity from peaks to troughs. Mean, standard deviation, and sequential variability were measured for both dynamics in each sentence. Analy...
متن کاملProduction of English Lexical Stress by Persian EFL Learners
This study examines the phonetic properties of lexical stress in English produced by Persian speakers learning English as a foreign language. The four most reliable phonetic correlates of English lexical stress, namely fundamental frequency, duration, intensity, and vowel quality were measured across Persian speakers’ production of the stressed and unstressed syllables of five English disyllabi...
متن کاملDoes it Groove or does it Stumble - Automatic Classification of Alcoholic Intoxication using Prosodic Features
This paper studies how prosodic features can help in the automatic detection of alcoholic intoxication. We compute features that have recently been proposed to model speech rhythm such as the pair-wise variability index for consonantal and vocalic segments (PVI) and study their aptness for the task. Further, we use a large prosodic feature vector modelling the usual candidates – pitch, intensit...
متن کاملSpeaker identification based on speech rhythm: the case of bilinguals
Voices are highly individual. The present study investigated how temporal characteristics of speech can contribute to speaker individuality for the same speaker speaking in different languages. By now there is a large body of evidence showing that measures based on temporal characteristics of consonantal and vocalic interval durations show drastic within language variability that is to a high d...
متن کامل