Singing Voice Interest Group

h1. Singing Voice and Artificial Intelligence academic forum reading group

* See the help button above, or "this page":https://code.soundsoftware.ac.uk/help/en/wiki_syntax.html, for how to format things - it isn't Markdown I'm afraid, but it is fairly simple all the same
* Use the History link at top-right (and then follow one of the Annotate links) to see who has edited which line
* Click the Watch link at top-right to request email notifications when the page is edited

This project is public. Please be cautious about including "private sharing links" and the like in wiki pages.

h3. Please contribute to these!
"topics suggestions":https://docs.google.com/spreadsheets/d/1MNOhxEJjgWFxFf8d0cX9HtWgvqPXM5Cr6YxZsEwZGBc/edit?usp=sharing
[[papers to discuss]]
"Datasets":https://docs.google.com/spreadsheets/d/1JeV58fUVYvVT4kp-dD-npUGGGoIM_evBT-5Re93USbc/edit?usp=sharing
our "youTube channel":https://www.youtube.com/channel/UCkH6d-ZqvTTJVJsHFF9_BKQ

During lockdown the meetings take place on Zoom at 3 pm BST (London), 4 pm W.Europe (Paris, Berlin), 7:30 pm IST (Mumbai), 11 pm Japan, 10 am EDT (New York), 7 am PDT (San Francisco)
"Google calendar":https://calendar.google.com/calendar/u/0?cid=cmNxbmZhZzRjNmJhZW91NW04bHRuZDhnaDBAZ3JvdXAuY2FsZW5kYXIuZ29vZ2xlLmNvbQ (shows meetings in your timezone)
Contact: proutskova at gmail dot com
__________________________________________________________________

h2. 27/07
* John McBride on information-theoretic modelling of discreteness in music perception

h2. 20/07
* Devansh Zurale
** source-filter models and deep learning models for voice synthesis
** Hindustani singing voice

h2. 29/06
* Yuto Ozaki: [[Agreement among human and automated transcriptions of global songs]]
* Discussion: roadmap to automatic transcription of cross-cultural vocal recordings

h2. 25/05
* Dadabots: [[Neural Synthesis - Eliminating Humans from Music]]

h2. 20/04
* Vincent Koops: [[AI Song Contest - Lessons on how to create in collaboration with AI]]
"video":https://youtu.be/CUbuI8woPF4

h2. 26/01/2021
* Prof. "Frank Scherbaum":https://www.uni-potsdam.de/en/soundscapelab/ : [["From Musical Acoustics of the Earth to Computational Ethnomusicology of Traditional Georgian Vocal Music"]]

h2. 19/01/2021
* Polina Proutskova and Olga Velichkina
[[Open questions on tonality perception and construction in non-Western vocal music]]
OR
What makes singing so difficult for automatic analysis
"video":https://www.youtube.com/watch?v=PkvoJPDohvQ

h2. 24/11
* Matan Gover
** [[Score-informed source separation of choral music]], "video":https://youtu.be/q-GwGwD9018
** on [[VoctroLabs current work]], "video":https://youtu.be/reEKrmEZseM

h2. 17/11
* Emir Demirel:
** [[Computational Pronunciation Analysis and Modeling of Sung Utterances]]
** [[Low Resource audio-to-lyrics alignment from polyphonic music recordings]]

h2. 27/10
* Helene Cuesta and Sebastian Rosenzweig: [["Polyphonic Singing Datasets for MIR Research"]], "video":https://youtu.be/Z6B6dQ1HOko

h2. 20/10
* ISMIR reports
* Brendan O'Connor: ""An Exploratory Study of Perceptual Spaces of the Singing Voice”

h2. 29/09
* Bernd Brabec de Mori & Victor A. Stoichițӑ: *"Postures of listening and vocal agencies"* [[abstract and bios]], "video":https://www.youtube.com/watch?v=k73J9fg_WJk&feature=youtu.be

h2. 22/09
* Pritish Chandna: [[""Deep Learning Applied to SATB Choirs"]]
* Kilian Schulze-Foster: [["Text-Informed Singing Voice Separation and Phoneme Level Lyrics Alignment"]]

h2. 18/08
* Courtney Reed: Singer's auditory imagery with altered auditory feedback [[abstract]]

h2. 07/07
* Prof. "Johan Sundberg":https://www.researchgate.net/profile/Johan_Sundberg : Physiological and acoustical aspects of phonation types - "video":https://www.youtube.com/watch?v=vwQQzYvX08o&t=2s

h2. 30/06
* Prof. "David Howard":http://www.davidmhoward.com/?LMCL=fuiq8C : "Pitch in singing is not all one might think it is."

h2. 19/05
* Emir Demirel on [[prosody and pronunciation in singing]]

h2. 17/03
* Paper quick read and discussion: [["CONTENT BASED SINGING VOICE EXTRACTION FROM A MUSICAL MIXTURE"]]
on Skype: https://join.skype.com/ddb39kV1HHvk

h2. 11/02
* Singing voice generation: [["A Neural Parametric Singing Synthesizer Modeling Timbre and Expression from Natural Songs"]]

h2. 21/01/2020
* [[Singing voice generation]]

h2. 10/12
*4 pm GC114*
* [[Universality and diversity in human song]] - discussing the Science paper from the Natural History of Song project

*5 pm : SCR bar*
* _*[[Christmas Big Sing!]]*_
* join us to sing Christmas songs from different cultures. Bring songs from your country and teach us

h2. 29/10 : Laws 3.06
* Expressivity in singing: paper [[suggestions]]

h2. 22/10 : Laws 3.06
* Prof. Simon Dixon: "Measuring and Modelling Intonation and Temperament"

h2. 15/10 : Laws 3.06
* Vocal physiology

h2. 01/10 NB different time slot! *2- 3 pm* : Laws 3.08C
* Wenming Gui on his research into singing voice detection and deep learning

h2. 17/09   : Laws 3.08D
* [[Charis Saitis]] on his research on timbre and its applications to singing voice

h2. 10/09 : ArtsOne 1.25
* "Polina on PEVoC 2019":https://photos.app.goo.gl/tnnywH3xFijM1DpJ9

h2. 23/07
* [[VocalSet with Courtney and Emir]]

h2. 16/07 : Bancroft: 1.03
* Emir reports from UK Speech Conference
* Emir introduces [[DAMP Intonation dataset]]
* Polina: [[report from FMA]]

h2. 02/07 : Eng402 Daphne Oram room
Small group, short topics
* [[Synthetic Voice Datasets]]
* [[Research on Vocal Tract transformations]]
* Informal discussion on vocal differences between cultures and classes

h2. 18/06 : GC604
* [[Chris 10 min presentation]]
* Emir presenting his [[poster for UK Speech Conference]]

h2. 11/06 : GC604
* 10 min presentations:
> * [[Wenming]]
> * [[Yukun]]
* "Datasets":https://docs.google.com/spreadsheets/d/1JeV58fUVYvVT4kp-dD-npUGGGoIM_evBT-5Re93USbc/edit?usp=sharing

h2. 04/06
* 10 min presentations:
> * [[Courtney]]
> * [[Brendan]]
* [[Datasets]]

h2. 28/05/19 : ITL

* First meeting,
* [[introduction]],
* [[coordination]]