Current Issue : October - December Volume : 2018 Issue Number : 4 Articles : 5 Articles
This paper builds a link between isolated domains within the arts and sciences, specifically\nbetween music and psychiatry. An analogous model is presented that associates heavy metal music\nwith bipolar disorder, a form of mental illness. Metal music consists of a variety of subgenres with\ndistinct manifestations of song, rhythm, instrumentation, and vocal structure. These manifestations\nare analogous to the symptomatology of bipolar disorder, specifically the recurrent episodes of\n(hypo)mania and depression. Examples of songs are given which show these analogies. Besides\ncreating a subjective link between apparently unconnected knowledge domains, these analogies\ncould play a heuristic role in clinical applications and education about the disorder and mental\nillnesses at large....
Music information retrieval (MIR) methods offer interesting possibilities for automatically\nidentifying time points in music recordings that relate to specific brain responses. However, how\nthe acoustical features and the novelty of the music structure affect the brain response is not yet\nclear. In the present study, we tested a new method for automatically identifying time points of brain\nresponses based on MIR analysis. We utilized an existing database including brain recordings of\n48 healthy listeners measured with electroencephalography (EEG) and magnetoencephalography\n(MEG). While we succeeded in capturing brain responses related to acoustical changes in the modern\ntango piece Adios Nonino, we obtained less reliable brain responses with a metal rock piece and a\nmodern symphony orchestra musical composition. However, brain responses might also relate to the\nnovelty of the music structure. Hence, we added a manual musicological analysis of novelty in the\nmusical structure to the computational acoustic analysis, obtaining strong brain responses even to\nthe rock and modern pieces. Although no standardized method yet exists, these preliminary results\nsuggest that analysis of novelty in music is an important aid to MIR analysis for investigating brain\nresponses to realistic music....
In magnetic resonance imaging (MRI), a patient is exposed to beat-like knocking sounds,\noften interrupted by periods of silence, which are caused by pulsing currents of the MRI scanner.\nIn order to increase the patient�s comfort, one strategy is to play back ambient music to induce positive\nemotions and to reduce stress during the MRI scanning process. To create an overall acceptable\nacoustic environment, one idea is to adapt the music to the locally periodic acoustic MRI noise.\nMotivated by this scenario, we consider in this paper the general problem of adapting a given\nmusic recording to fulfill certain temporal constraints. More concretely, the constraints are given\nby a reference time axis with specified time points (e.g., the time positions of the MRI scanner�s\nknocking sounds). Then, the goal is to temporally modify a suitable music recording such that its beat\npositions align with the specified time points. As one technical contribution, we model this alignment\ntask as an optimization problem with the objective to fulfill the constraints while avoiding strong\nlocal distortions in the music. Furthermore, we introduce an efficient algorithm based on dynamic\nprogramming for solving this task. Based on the computed alignment, we use existing time-scale\nmodification procedures for locally adapting the music recording. To illustrate the outcome of our\nprocedure, we discuss representative synthetic and real-world examples, which can be accessed via\nan interactive website. In particular, these examples indicate the potential of automated methods for\nnoise beautification within the MRI application scenario....
This paper proposes a note-based music language model (MLM) for improving note-level\npolyphonic piano transcription. The MLM is based on the recurrent structure, which could model the\ntemporal correlations between notes in music sequences. To combine the outputs of the note-based\nMLM and acoustic model directly, an integrated architecture is adopted in this paper. We also\npropose an inference algorithm, in which the note-based MLM is used to predict notes at the blank\nonsets in the thresholding transcription results. The experimental results show that the proposed\ninference algorithm improves the performance of note-level transcription. We also observe that\nthe combination of the restricted Boltzmann machine (RBM) and recurrent structure outperforms\na single recurrent neural network (RNN) or long short-term memory network (LSTM) in modeling\nthe high-dimensional note sequences. Among all the MLMs, LSTM-RBM helps the system yield the\nbest results on all evaluation metrics regardless of the performance of acoustic models....
Mobile devices are often used in our daily lives for the purposes of speech and\ncommunication. The speech quality of mobile devices is always degraded due to the environmental\nnoises surrounding mobile device users. Regretfully, an effective background noise reduction solution\ncannot easily be developed for this speech enhancement problem. Due to these depicted reasons,\na methodology is systematically proposed to eliminate the effects of background noises for the speech\ncommunication of mobile devices. This methodology integrates a dual microphone array with a\nbackground noise elimination algorithm. The proposed background noise elimination algorithm\nincludes a whitening process, a speech modelling method and an H2 estimator. Due to the adoption\nof the dual microphone array, a low-cost design can be obtained for the speech enhancement of\nmobile devices. Practical tests have proven that this proposed method is immune to random\nbackground noises, and noiseless speech can be obtained after executing this denoise process....
Loading....