A Mouth Opening Effect Based on Pole Modification for Expressive Singing Voice Transformation

Ardaillon, Luc; Röebel, Axel

doi:10.21437/interspeech.2017-1453

Cited by 2 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Sebaliknya, penyanyi pop dapat menyanyikan nada yang bisa didengar dengan bantuan mikrofon. Faktor lain yang perlu dipertimbangkan adalah penggunaan berbagai bentuk produksi vocal (Ardaillon, 2017).…”

Section: Ambitus Suara (Vocal Range)unclassified

Pengaruh Nyanyian Buku Ende terhadap Kualitas Bernyanyi Jemaat Gereja HKBP Yogyakarta

Sitinjak

2023

Resital

View full text Add to dashboard Cite

The Influence of the Buku Ende Hymn on the Quality of Singing Among the Congregation of the HKBP Church in Yogyakarta. This paper talks about Ende book, a collection of worship songs for the HKBP congregation composed by European composers in the 16th and 17th centuries. Conveyed by missionaries to Batak land, these songs were later translated into Toba Batak language and some were composed to suit the rhythms of Batak indigenous music. In singing the songs, HKBP Yogyakarta congregation sing the original notation (not transfused lower) that frequently consists of high notes, causing the congregation having low vocal range to sing the song in one octave below the basic tone. The objective of the study is to examine how immense Ende Book influences the vocal quality of HKBP Yogyakarta congregation. The author implemented descriptive qualitative method by adapting the theory of 'The Power of Habit' by Charles Duhigg. Data collection techniques used by the author were observation, interview, and documentation. The results of this study reveal that habit plays a major role in the routines to achieve a satisfactory quality of singing. When singing Ende book, HKBP Yogyakarta congregation have unconsciously acquainted several elements of vocal techniques. The vocal techniques in particular are breathing, resonance, voice range, and interpretation, in which a significant impact on the quality of the singing voices of HKBP Yogyakarta congregation retain. By implementing the original range and sentence structure (phrasing) in Ende book, the learning process taken place e every Sunday worshipping has unconsciously imporoved the singing quality of HKBP Yogyakarta congregation.ABSTRAKBuku Ende merupakan buku yang berisi nyanyian ibadah bagi jemaat HKBP yang sebagian besar diciptakan oleh komponis Eropa pada abad ke-16 dan ke-17 Masehi. Nyanyian ini dibawa oleh para misionaris ke tanah Batak lalu diterjemahkan ke dalam bahasa Batak Toba dan ada juga yang digubah untuk disesuaikan dengan irama musik Batak. Menyanyikan nyanyian buku Ende ini jemaat HKBP Yogyakarta bernyanyi dengan tangga nada aslinya (tidak ditransfus lebih rendah) sehingga ketika menyanyikan nada-nada tinggi, bagi jemaat yang mempunyai ambitus suara yang rendah sering menyanyikannya dengan nada satu oktaf dibawah nada dasar. Tujuan dari penelitian ini untuk melihat sejauh mana pengaruh nyanyian pada Buku Ende ini terhadap kualitas bernyanyi jemaat HKBP Yogyakarta. Penelitian ini menggunakan metode deskriptif kualitatif dengan memakai teori ‘The Power of Habit’ dari Charles Duhigg. Teknik pengumpulan data dengan cara observasi, wawancara, dan dokumentasi. Hasil penelitian ini menunjukkan bahwa faktor kebiasaan menjadi salah satu rutinitas untuk mencapai kualitas bernyanyi yang memuaskan. Dalam menyanyikan buku Ende ini terdapat banyak unsur-unsur teknik vokal yang tanpa disadari telah memberikan pembelajaran vokal, khususnya kepada jemaat HKBP Yogyakarta. Teknik vokal yang dimaksud, antara lain: pernapasan, resonansi, ambitus suara, dan interpretasi, berdampak besar bagi kualitas suara bernyanyi jemaat HKBP Yogyakarta. Dengan nyanyikan tangga nada asli pada buku Ende dan kebiasaan menerapkan teknik vokal yang baik dan benar, tanpa disadari proses pembelajaran berlangsung setiap Minggu. Hal ini yang menyebabkan suara jemaat gereja HKBP Yogyakarta semakin berkualitas baik.

show abstract

Section: Ambitus Suara (Vocal Range)unclassified

Pengaruh Nyanyian Buku Ende terhadap Kualitas Bernyanyi Jemaat Gereja HKBP Yogyakarta

Sitinjak

2023

Resital

View full text Add to dashboard Cite

show abstract

“…We will use three different training datasets: a pure singing voice dataset si, a pure speech dataset sp, and a combined dataset vo consisting of both singing and speech. We use the same singing voice dataset as in [6] and [10], which consists of the datasets from [21,22,23,24,25,26,27,13,28,29]. The speech dataset consists of VCTK [30], Att-HACK [31], and further internal datasets containing expressive speech, amounting to about 70 h of speech in total.…”

Section: Training Datamentioning

confidence: 99%

“…During the age of classical parametric vocoders, the lower level voice attributes, like the pitch or voice level, could be transformed by adjusting the vocoder parameters according to the desired change of the voice attributes using predetermined heuristics [8,9,7]. To create realistic transformations, however, even changing the pitch is not as straightforward as simply changing the f0 parameter [11,12,13]: Because parameters of real voice signals are not independent, a change in one parameter needs to be accompanied by a change in the other parameters.…”

Section: Introductionmentioning

confidence: 99%

A Bottleneck Auto-Encoder for F0 Transformations on Speech and Singing Voice

Bous

Röebel

2022

Information

View full text Add to dashboard Cite

In this publication, we present a deep learning-based method to transform the f0 in speech and singing voice recordings. f0 transformation is performed by training an auto-encoder on the voice signal’s mel-spectrogram and conditioning the auto-encoder on the f0. Inspired by AutoVC/F0, we apply an information bottleneck to it to disentangle the f0 from its latent code. The resulting model successfully applies the desired f0 to the input mel-spectrograms and adapts the speaker identity when necessary, e.g., if the requested f0 falls out of the range of the source speaker/singer. Using the mean f0 error in the transformed mel-spectrograms, we define a disentanglement measure and perform a study over the required bottleneck size. The study reveals that to remove the f0 from the auto-encoder’s latent code, the bottleneck size should be smaller than four for singing and smaller than nine for speech. Through a perceptive test, we compare the audio quality of the proposed auto-encoder to f0 transformations obtained with a classical vocoder. The perceptive test confirms that the audio quality is better for the auto-encoder than for the classical vocoder. Finally, a visual analysis of the latent code for the two-dimensional case is carried out. We observe that the auto-encoder encodes phonemes as repeated discontinuous temporal gestures within the latent code.

show abstract

A Mouth Opening Effect Based on Pole Modification for Expressive Singing Voice Transformation

Cited by 2 publications

References 17 publications

Pengaruh Nyanyian Buku Ende terhadap Kualitas Bernyanyi Jemaat Gereja HKBP Yogyakarta

Pengaruh Nyanyian Buku Ende terhadap Kualitas Bernyanyi Jemaat Gereja HKBP Yogyakarta

A Bottleneck Auto-Encoder for F0 Transformations on Speech and Singing Voice

Contact Info

Product

Resources

About