| 1. |
|
|
| 2. |
|
|
| 3. |
- Ahlbäck, Sven, 1960-
(författare)
-
MSTRE-Net: Multistreaming Acoustic Modeling for Automatic Lyrics Transcription
- 2021
-
Konferensbidrag (refereegranskat)abstract
- This paper makes several contributions to automatic lyrics transcription (ALT) research. Our main contribution is a novel variant of the Multistreaming Time-Delay Neural Network (MTDNN) architecture, called MSTRE-Net, which processes the temporal information using multiple streams in parallel with varying resolutions keeping the network more compact, and thus with a faster inference and an improved recognition rate than having identical TDNN streams. In addition, two novel preprocessing steps prior to training the acoustic model are proposed. First, we suggest using recordings from both monophonic and polyphonic domains during training the acoustic model. Second, we tag monophonic and polyphonic recordings with distinct labels for discriminating non-vocal silence and music instances during alignment. Moreover, we present a new test set with a considerably larger size and a higher musical variability compared to the existing datasets used in ALT literature, while maintaining the gender balance of the singers. Our best performing model sets the state-of-the-art in lyrics transcription by a large margin. For reproducibility, we publicly share the identifiers to retrieve the data used in this paper.
|
|
| 4. |
- Ahlbäck, Sven, 1960-
(författare)
-
Pitch-Informed Instrument Assignment using a Deep Convolutional Network with Multiple Kernel Shapes
- 2021
-
Konferensbidrag (refereegranskat)abstract
- This paper proposes a deep convolutional neural network for performing note-level instrument assignment. Given a polyphonic multi-instrumental music signal along with its ground truth or predicted notes, the objective is to assign an instrumental source for each note. This problem is addressed as a pitch-informed classification task where each note is analysed individually. We also propose to utilise several kernel shapes in the convolutional layers in order to facilitate learning of timbre-discriminative feature maps. Experiments on the MusicNet dataset using 7 instrument classes show that our approach is able to achieve an average F-score of 0.904 when the original multi-pitch annotations are used as the pitch information for the system, and that it also excels if the note information is provided using third-party multi-pitch estimation algorithms. We also include ablation studies investigating the effects of the use of multiple kernel shapes and comparing different input representations for the audio and the note-related information.
|
|
| 5. |
- Atienza, Ricardo, et al.
(författare)
-
Playing the design : Creating soundscapes through playful interaction
- 2023
-
Ingår i: SMC 2023 - Proceedings of the Sound and Music Computing Conference 2023. - : Sound and Music Computing Network. ; , s. 362-369
-
Konferensbidrag (refereegranskat)abstract
- This study takes inspiration from provocative design methods to gain knowledge on sound preferences regarding future vehicles’ designed sounds. A particular population subset was a triggering component of this study: people with hearing impairments. To that aim, we have developed a public installation in which to test a hypothetical futuristic city square. It includes three electrical vehicles whose sound can be designed by the visitor. The interface allows the user to interact and play with a number of provided sonic textures within a real-time web application, thus “playing” the design. This opens a design space of three distinct sounds that are mixed into an overall soundscape presented in a multichannel immersive environment. The paper describes the design processes involved.
|
|
| 6. |
- Falkenberg, Kjetil, Docent, 1972-, et al.
(författare)
-
Creating digital musical instruments with and for children: Including vocal sketching as a method for engaging in codesign
- 2020
-
Ingår i: Human Technology. - : Centre of Sociological Research, NGO. - 1795-6889. ; 16:3, s. 348-371
-
Tidskriftsartikel (refereegranskat)abstract
- A class of master of science students and a group of preschool children codesigned new digital musical instruments based on workshop interviews involving vocal sketching, a method for imitating and portraying sounds. The aim of the study was to explore how the students and children would approach vocal sketching as one of several design methods. The children described musical instruments to the students using vocal sketching and other modalities (verbal, drawing, gestures). The resulting instruments built by the students were showcased at the Swedish Museum of Performing Arts in Stockholm. Although all the children tried vocal sketching during preparatory tasks, few employed the method during the workshop. However, the instruments seemed to meet the children’s expectations. Consequently, even though the vocal sketching method alone provided few design directives in the given context, we suggest that vocal sketching, under favorable circumstances, can be an engaging component that complements other modalities in codesign involving children.
|
|
| 7. |
- Frid, Emma, 1988-, et al.
(författare)
-
Haptic Music : Exploring Whole-Body Vibrations and Tactile Sound for a Multisensory Music Installation
- 2020
-
Ingår i: Proceedings of the Sound and Music Computing Conference (SMC) 2020. - Torino, Italy. ; , s. 68-75
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a study on the composition of haptic music for a multisensory installation and how composers could be aided by a preparatory workshop focusing on the perception of whole-body vibrations prior to such a composition task. Five students from a Master’s program in Music Production were asked to create haptic music for the installation Sound Forest. The students were exposed to a set of different sounds producing whole-body vibrations through a wooden platform and asked to describe perceived sensations for respective sound. Results suggested that the workshop helped the composers successfully complete the composition task and that awareness of haptic possibilities of the multisensory installation could be improved through training. Moreover, the sounds used as stimuli provided a relatively wide range of perceived sensations, ranging from pleasant to unpleasant. Considerable intra-subject differences motivate future large-scale studies on the perception of whole-body vibrations in artistic music practice.
|
|
| 8. |
- Frid, Emma, 1988-, et al.
(författare)
-
Sound Forest - Evaluation of an Accessible Multisensory Music Installation
- 2019
-
Ingår i: Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems. - New York, NY, USA : ACM. - 9781450359702 ; , s. 1-12
-
Konferensbidrag (refereegranskat)abstract
- Sound Forest is a music installation consisting of a room with light-emitting interactive strings, vibrating platforms and speakers, situated at the Swedish Museum of Performing Arts. In this paper we present an exploratory study focusing on evaluation of Sound Forest based on picture cards and interviews. Since Sound Forest should be accessible for everyone, regardless age or abilities, we invited children, teens and adults with physical and intellectual disabilities to take part in the evaluation. The main contribution of this work lies in its fndings suggesting that multisensory platforms such as Sound Forest, providing whole-body vibrations, can be used to provide visitors of diferent ages and abilities with similar associations to musical experiences. Interviews also revealed positive responses to haptic feedback in this context. Participants of diferent ages used diferent strategies and bodily modes of interaction in Sound Forest, with activities ranging from running to synchronized music-making and collaborative play.
|
|
| 9. |
- Gullö, Jan-Olof, 1961-
(författare)
-
‘50 years of “Smoke on the Water”: What can we learn?’
- 2023
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- The song "Smoke on the Water", recorded by the British rock group Deep Purple in December 1971, had a global reach, and contributed much to Deep Purple's success and fandom. The song was recorded during a sound check when the band was jamming and trying out a location for a recording session and was initially not intended to be released. A turning point was a successful live album, "Made in Japan", in 1972, including the song. And over the years, the song has retained its popularity among many. But how can the success of Smoke on the Water be explained? The study includes interviews with music teachers, music directors, music students and musicians in different countries, as well as interviews with some original members of Deep Purple. The findings are empirically surprising and indicate tension regarding understanding what is most important in a specific musical performance and piece of music or recording, such as Smoke on the Water, between those who perform or produce and those who listen. In short, for many of those who study music and music production, the details of the music and various intrinsic aspects of musical content seem to be more important, compared to those who are more average listeners who seem to pay more attention to how the lyrics and music speak to them. Therefore, the results can help to highlight some possible areas of development. At least for those students who want to produce music and reach listeners who cannot analyse music and deeply understand various advanced musical aspects as well as they themselves can.
|
|
| 10. |
- Gullö, Jan-Olof, 1961-
(författare)
-
Let´s Clear the Smoke: Fifty Years of Smoke on the Water in Music Education
- 2023
-
Ingår i: MEIEA Summit Proceedings - 2023. - Nashville : Belmont University & MEIEA. ; , s. 23-26
-
Konferensbidrag (refereegranskat)abstract
- In December 1971, the British rock band Deep Purple recorded Smoke on the Water, which became a global hit and significantly contributed to the band’s popularity. This study aims to investigate the reasons behind the song’s success, such as its inherent values, composition, lyrics, or music production design, as well as other potential explanations. We also study Smoke on the Water’s impact on music education. We interviewed music teachers, producers, students, and musicians from different countries to accomplish this. The study also relies on insights from interviews with Deep Purple members, observations made during concerts and study visits, and external sources. The study finds its theoretical basis in cultural psychology, education, economics, sociology, and musicology theories. The findings highlight the significance of understanding the fundamental elements of a song, which aspiring artists, musicians, and music producers should consider if they want to reach a broader audience.
|
|
