MUSICAL-MOODS · A mood-indexed database of scores, lyrics, musical excerpts, vector-based 3D animations, and dance video recordings
„Хоризонт 2020“ — Действия „Мария Склодовска-Кюри“
- Период
- 2015-12-01 → 2019-04-02
- Финансиране от ЕС
- 244 269 €
- Участници
- 2
- Схема
- MSCA-IF-GF
Линиите свързват координатора с партньорите.
Накратко на български
Музикалните емоции и психическите състояния се анализират чрез база данни с ноти, текстове, танци и 3D анимации. Това помага за подобряване на музикалната терапия, образованието и създаването на интелигентни системи за разпознаване на настроения.
Кратко обяснение, генерирано от езиков модел по текста на CORDIS. Оригиналът е по-долу.
Резултати накратко
A mood-indexed database of scores, lyrics, musical excerpts, vector-based 3D animations, and dance video recordings
Musical-Moods aimed at enabling the capacity to classify and recognize emotions and mental states from multimedia data in interactive and intelligent music systems. Examples of application include the profiling of users and databases for creative and media industries, improving access for citizens and researchers to musical heritage, services for audio on demand, education and training activities, music therapy, and music making. OBJECTIVES and CONCLUSIONS 1) Dept. of Cognitive Sciences, University of California, Irvine (UCI): A multimodal game with a purpose for Internet users was developed and deployed online (M-GWAP), drawing from preliminary lyrics corpus data of opera works in the public domain and transcription of language data from interviews to dancers. 2) Dept. of Dance, UCI: A multimodal database was realized (audio, video, motion capture, language data), for mood indexing in terms of dancers' embodied cognition and automatic music generation. 3) Dept. of Electronic Engineering, University of Rome Tor Vergata (UNITOV): A music mood classification model was implemented by leveraging on domain experts' knowledge.
Текст от CORDIS, на английски · Данни: CORDIS, © Европейски съюз
Цел на проекта
The project aims at the development of an online database of scores, lyrics and musical excerpts, vector-based 3D animations, and dance video recordings, indexed by mood. Such a taxonomy of relations between the musical, linguistic and motion domains will be aimed at interactive music systems and music making. For realising the database, digital scores inclusive of lyrics will be gathered from collections of music in the public domain. Music mood classification using audio and metadata will aim at capturing sophisticated features but using no explicit domain-specific knowledge about a mental state. Datasets will be realised through a cross-modal approach. Validation of the model will be carried out by combining results from an online game-with-a-purpose, for Internet users, and from intermedia case studies for selected dancers. In further case studies, music works will be realised, also by invited artists, for the evaluation of the database in interactive music making. An online call for artists to use the database in music making or sound generation will be aimed at extending the evaluation further. The final database will be made available online for further exploitation. The present research will generate new knowledge for use in next-generation systems of interactive music and music emotion recognition, also contributing to extend the investigation in the broader areas of music making, computational creativity and information retrieval.
Оригинален текст от CORDIS (на английски).
Участници
- UNIVERSITA DEGLI STUDI DI ROMA TOR VERGATA · RomaКоординаторИталия
- THE REGENTS OF THE UNIVERSITY OF CALIFORNIA · OaklandСъединени щати
Връзки
Данни: CORDIS, © Европейски съюз