Acoustic properties of phonemes in continuous speech for different speaking rate
نویسنده
چکیده
Investigations have been made on the perceptual and acoustic properties of individual phonemes in continuous speech for different speaking rate. Fifteen short sentences spoken by four male speakers have been used as the test material. Each speaker has been asked to pronounce the sentences with three different rates: normal, first and slow. For perceptual experiment, individual CV-syllables have been taken out from their contexts and presented to listeners in isolation to be identified. The results reveal that individual syllables in continuous speech do not have enough phonetic information to be correctly identified especially for the fast speech. The average identification of syllables for the fast speech is 35% and even vowels are identified less than 60%. Slow speech shows highest identification among the three rates; 86% for the syllables, 87% for the consonants and 91% for the vowels. Duration of consonants and vowels are both affected by the speaking rate and the latter has been found greater in change. An important finding is that the duration ratio between consonant and vowel of a CV-syllable in the fast speech is kept almost the same as that in the normal speech. Vowel lengthening in the slow speech becomes significantly large. Formant frequencies of individual vowels have largely shifted toward the neutral region in the conventional F1-F2 plane as the rate becomes fast and, at the same time, distribution of vowels in each category becomes large.
منابع مشابه
Perceptual and Acoustic Properties of Phonemes in Continuous Speech for Different Speaking Rate
Investigations have been made on the perceptual and acoustic properties of individual phonemes in continuous speech for different speaking rate. Fifteen short sentences spoken by four male speakers have been used as the test material. Each speaker has been asked to pronounce the sentences with three different rates: normal, first and slow. For perceptual experiment, individual CV-syllables have...
متن کاملA Reassessment of Temporal Information in Speech Processing
The work described in this paper has been motivated by consideration of both parsimony in the representation of speech acoustics and observations of the degradation of automatic speech recognition (ASR) performance when speaking rate changes. The acoustic-phonetic processing within an ASR system involves the matching of a representation of the acoustic stream with a phoneme symbol sequence that...
متن کاملMeasuring Acoustic Reduction in Feature Space
Modelling varying speaking style remains a challenge to state of the art speech recognition and synthesis systems. Vowel and consonant reduction have been identified as correlative to speaking style variation, but still lack a common measurement. The reduction phenomena are often observed without consideration of coarticulation and assimilation effects, and as a result of speaking rate variabil...
متن کاملVocal Pathologies Detection and Mispronounced Phonemes Identification: Case of Arabic Continuous Speech
We propose in this work a novel acoustic phonetic study for Arabic people suffering from language disabilities and non-native learners of Arabic language to classify Arabic continuous speech to pathological or healthy and to identify phonemes that pose pronunciation problems (case of pathological speeches). The main idea can be summarized in comparing between the phonetic model reference to Ara...
متن کاملEfficient Acoustic Modeling Method for Unsupervised Speech Recognition using Multi-Task Deep Neural Network
This paper proposes a method of acoustic modeling for zero-resourced languages speech recognition under mismatch conditions. In those languages, very limited or no transcribed speech is available for traditional monolingual speech recognition. Conventional methods such as IPA based universal acoustic modeling has been proved to be effective under matched acoustic conditions (similar speaking st...
متن کامل