Estimation of formant frequencies in infant cry

“…Kajian lain oleh Robb et al [7] mendapatkan rerata f • pada bayi normal sekitar 512 Hz, sementara kajian Lind et al [8] menemukan bahwa nilai f • bernilai 450 Hz. Bard et al [9] dan Lagasse et al [10] Makalah ini menyajikan pendekatan berbeda dengan analisis ekstraksi ciri didasarkan atas nilai Mel Frequency Cepstral Coefficient (MFCC) pada sinyal tangis bayi yang kemudian dimanfaatkan untuk visualisasi lanjutan menggunakan dynamic time warping (DTW).…”

unclassified

Analisis Spektrum Akustik Tangis Bayi Penderita Penyakit Jantung Bawaan menggunakan Teknik Dynamic Time Warping

Afifah

Yahya

Nuryani

et al. 2016

JFA

View full text Add to dashboard Cite

IntisariPaper ini berfokus pada kajian perbandingan spektral tangis bayi penderita penyakit jantung bawaan (Congenital Heart Disease, CHD) dan tangis bayi normal menggunakan teknik Dynamic Time Warping (DTW). Sebanyak sepuluh sampel tangis bayi penderita CHD dan bayi normal berusia kurang dari satu bulan direkam menggunakan Sony IC-Recorder tipe ICD-PX333. Data digital kemudian diproses menggunakan piranti lunak Speech Filing System (SFS) untuk mendapatkan f•, formants, dan nilai Mel-Frequency Cepstral Coefficients (MFCC) sebagai penciri spektral yang kemudian divisualkan dengan DTW. Hasil kajian menunjukkan bahwa ciri spektral tangis bayi penderita CHD mempunyai tingkat perbedaan signifikan terhadap tangis bayi normal. Di samping itu ditemukan anomali yang diduga berkait dengan irisan dalam bentang frekuensi ambang maupun formant tangis bayi normal dan penderita CHD. AbstractThis paper emphasizes on acoustics spectral similarity analysis on of normal infant cry compared to infant spectrum with Congenital Heart Disease (CHD). Ten of the cries signals of infant with CHD and normal baby aged less than a month were recorded by using Sony IC-Recorder ICD-PX333. The Speech Filing System software utilized for estimating fundamental frequency, formants, and MFCCs were used as cry spectral characteristics to be visualized using Dynamic Time Warping (DTW) technique. The result shows that both group partially has significant different characteristics since anomalies occurred which is considered due to the intersection on the values of fundamental frequency and formants of the both groups.

show abstract

“…The limitations of this method are well known, and expositions of the hypothetical advantages and disadvantages appear in popular texts (for example, Johnson, 1997). In practice, there are relatively few reports that calibrate the efficacy of linear prediction in comparison to the unquestionably more laborious method of estimation by hand (for example, Assmann and Katz, 2005;Nearey et al, 2002;Robb and Cacace, 1995). Here, new measures comparing linear prediction and manual estimation are reported, motivated by an empirical aim to estimate the magnitude of the errors that accumulate and by a practical aim to appraise the potential of linear prediction for creating synthesis parameters in the production of sine-wave speech.…”

Section: Introductionmentioning

confidence: 99%

Estimating speech spectra for copy synthesis by linear prediction and by hand

Remez

Dubowski

Davids

et al. 2011

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

Linear prediction is a widely available technique for analyzing acoustic properties of speech, although this method is known to be error-prone. New tests assessed the adequacy of linear prediction estimates by using this method to derive synthesis parameters and testing the intelligibility of the synthetic speech that results. Matched sets of sine-wave sentences were created, one set using uncorrected linear prediction estimates of natural sentences, the other using estimates made by hand. Phoneme restrictions imposed on linguistic properties allowed comparisons between continuous and intermittent voicing, oral or nasal and fricative manner, and unrestricted phonemic variation. Intelligibility tests revealed uniformly good performance with sentences created by handestimation and a minimal decrease in intelligibility with estimation by linear prediction due to manner variation with continuous voicing. Poorer performance was observed when linear prediction estimates were used to produce synthetic versions of phonemically unrestricted sentences, but no similar decline was observed with synthetic sentences produced by hand estimation. The results show a substantial intelligibility cost of reliance on uncorrected linear prediction estimates when phonemic variation approaches natural incidence.

show abstract

Estimation of formant frequencies in infant cry

Cited by 28 publications

References 32 publications

The neonate cry after cesarean section and vaginal delivery during the first minutes of life

The neonate cry after cesarean section and vaginal delivery during the first minutes of life

Analisis Spektrum Akustik Tangis Bayi Penderita Penyakit Jantung Bawaan menggunakan Teknik Dynamic Time Warping

Estimating speech spectra for copy synthesis by linear prediction and by hand

Contact Info

Product

Resources

About