Identification of correlation between blood relations using speech signal

Padmini, Palli; Tripathi, Shikha; Bhowmick, Kaustav

doi:10.1109/spices.2017.8091341

Cited by 1 publication

(4 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Studies of voice pairs like father and son or twins [30] revealed that the first harmonic of the voice signals, "f 0 ," [31], showed some correlation in the pairs, with conformational [32,33]. The present author and the group have previously reported a preliminary work on the correlation of voices based on features availability use to blood relations [34], which shows the closeness of formants in voices of relatives, towards the natural voice.…”

Section: Introductionmentioning

confidence: 74%

“…The correlation [34] between the resynthesized speech and the voice samples from the corpus is classified using SVM. It provides results based on feature extraction and matching of voice samples, parameter setting, acoustic analysis to find the correlation, and classification of the correlation as either strong or weak, which are discussed briefly in the following sections.…”

Section: Classification Of Correlation Percentage Between Original and Resynthesized Blood Relation Voice Samplesmentioning

confidence: 99%

“…We consider a number of centroids k = 8 (∼number of groups in the data) for effective results. In the previous preliminary work by the author, the steps for feature extraction and matching are explained in detail along with results for the Sanskrit language sentence [34].…”

Section: Feature Extraction and Matchingmentioning

confidence: 99%

“…The importance of the present work is that (a) ageconversion of voice samples to suit a target's voice and, (b) whether the choice of voice sample should be from within family blood relations, or anywhere else, have been established. Prior studies in literature fall into two categories towards our present work motivation i.e., voice conversion techniques, mainly for gender conversion, which is frequency translation in effect [15][16][17][18][19][20][21][22][23][24][25] and about finding similarities between same accent voices [26][27][28][29][30][31][32][33][34] to achieve natural of speech or voice using various techniques, while the present work investigates family relation as a big factor to include natural features in voices. A voice conversion system should be able to identify the characteristics of an individual's speech (source speaker) and substitute them for those of another speaker (the target speaker) with reasonable loss of information or modification in the transferred message.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Age-Based Automatic Voice Conversion Using Blood Relation for Voice Impaired

Padmini¹,

Paramasivam²,

Lal³

et al. 2022

Computers, Materials &Amp; Continua

Self Cite

View full text Add to dashboard Cite

The present work presents a statistical method to translate human voices across age groups, based on commonalities in voices of blood relations. The age-translated voices have been naturalized extracting the blood relation features e.g., pitch, duration, energy, using Mel Frequency Cepstrum Coefficients (MFCC), for social compatibility of the voice-impaired. The system has been demonstrated using standard English and an Indian language. The voice samples for resynthesis were derived from 12 families, with member ages ranging from 8-80 years. The voice-age translation, performed using the Pitch synchronous overlap and add (PSOLA) approach, by modulation of extracted voice features, was validated by perception test. The translated and resynthesized voices were correlated using Linde, Buzo, Gray (LBG), and Kekre's Fast Codebook generation (KFCG) algorithms. For translated voice targets, a strong (θ >∼93% and θ >∼96%) correlation was found with blood relatives, whereas, a weak (θ <∼78% and θ <∼80%) correlation range was found between different families and different gender from same families. The study further subcategorized the sampling and synthesis of the voices into similar or dissimilar gender groups, using a support vector machine (SVM) choosing between available voice samples. Finally, ∼96%, ∼93%, and ∼94% accuracies were obtained in the identification of the gender of the voice sample, the age group samples, and the correlation between the original and converted voice samples, respectively. The results obtained were close to the natural voice sample features and are envisaged to facilitate a near-natural voice for speech-impaired easily.

show abstract

Section: Introductionmentioning

confidence: 74%

Section: Classification Of Correlation Percentage Between Original and Resynthesized Blood Relation Voice Samplesmentioning

confidence: 99%

Section: Feature Extraction and Matchingmentioning

confidence: 99%