Piano Genie

Donahue, Chris; Simon, Ian; Dieleman, Sander

doi:10.1145/3301275.3302288

Cited by 23 publications

(18 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different loss functions can be combined. For controlled audio synthesis [64], one loss function was customized to encourage the latent variables of a variational autoencoder (VAE) to remain inside a defined range and another to have changes in the control space be reflected in the generated audio. f) Phase modeling: In the calculation of the log-mel spectrum, the magnitude spectrum is used but the phase spectrum is lost.…”

Section: Modelsmentioning

confidence: 99%

Deep Learning for Audio Signal Processing

Purwins

Virtanen

et al. 2019

IEEE J. Sel. Top. Signal Process.

602

247

View full text Add to dashboard Cite

Given the recent surge in developments of deep learning, this article provides a review of the state-of-the-art deep learning techniques for audio signal processing. Speech, music, and environmental sound processing are considered sideby-side, in order to point out similarities and differences between the domains, highlighting general methods, problems, key references, and potential for cross-fertilization between areas. The dominant feature representations (in particular, log-mel spectra and raw waveform) and deep learning models are reviewed, including convolutional neural networks, variants of the long short-term memory architecture, as well as more audio-specific neural network models. Subsequently, prominent deep learning application areas are covered, i.e. audio recognition (automatic speech recognition, music information retrieval, environmental sound detection, localization and tracking) and synthesis and transformation (source separation, audio enhancement, generative models for speech, sound, and music synthesis). Finally, key issues and future questions regarding deep learning applied to audio signal processing are identified.

show abstract

Section: Modelsmentioning

confidence: 99%

Deep Learning for Audio Signal Processing

Purwins

Virtanen

et al. 2019

IEEE J. Sel. Top. Signal Process.

602

247

View full text Add to dashboard Cite

show abstract

“…Dove et al [209] surveyed to understand how design innovation is practiced in the ML domain in terms of user experience. [63], [70], [165], [174], [211] [124], [125], [128], [175], [217] [69], [112], [113], [118], [130], [131], [133], [135], [137], [140], [144], [152], [153], [155] [49], [57], [67], [98], [110], [114], [180], [192], [193], [203], [214], [215] [48], [59], [62], [75], [79], [111], [120], [156], [159], [185], [195], [197], [207], [218] [65], [83],…”

Section: Survey Resultsmentioning

confidence: 99%

“…Davis et al [ 152 ] is an intelligent drawing partner that can improvise and collaborate on abstract sketches. Piano Genie [ 153 ] is an intelligent controller for non-musicians to improvise on the piano. SViM [ 154 ] is an adaptive screen-magnifier tool for people with low vision to watch videos.…”

Section: Classifying Hcml Researchmentioning

confidence: 99%

“…Given that the majority in those sectors are not AI experts developing AI systems for them requires us to investigate the human aspect of such systems. Our analysis shows that application domains have specifically targeted gaming [63,70,165,174,211], interactive technologies [69,112,113,118,130,131,[133][134][135]137,140,144,152,153,155,212,213], medicine [49,57,67,110,114,180,192,193,203,214,215], psychiatry [98], music [65,83,85,102,153], sports [126], dating [60], video production [84], assistive technologies [2,80,86,88,89,…”

Section: Application Domainsmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Recent Deep Learning Approaches in Human-Centered Machine Learning

Kaluarachchi

Reis

Nanayakkara

2021

Sensors

View full text Add to dashboard Cite

After Deep Learning (DL) regained popularity recently, the Artificial Intelligence (AI) or Machine Learning (ML) field is undergoing rapid growth concerning research and real-world application development. Deep Learning has generated complexities in algorithms, and researchers and users have raised concerns regarding the usability and adoptability of Deep Learning systems. These concerns, coupled with the increasing human-AI interactions, have created the emerging field that is Human-Centered Machine Learning (HCML). We present this review paper as an overview and analysis of existing work in HCML related to DL. Firstly, we collaborated with field domain experts to develop a working definition for HCML. Secondly, through a systematic literature review, we analyze and classify 162 publications that fall within HCML. Our classification is based on aspects including contribution type, application area, and focused human categories. Finally, we analyze the topology of the HCML landscape by identifying research gaps, highlighting conflicting interpretations, addressing current challenges, and presenting future HCML research opportunities.

show abstract

“…One related approach includes Piano Genie, a system where novices are empowered to improvise on a piano using a controller with eight buttons [29]. The button presses are automatically translated into piano keypresses that musically make the most sense.…”

Section: Related Workmentioning

confidence: 99%

Enhanced Learning of Jazz Chords with a Projector Based Piano Keyboard Augmentation

Sandnes

Eika

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Learning jazz piano is considered technically difficult. Most people cannot afford private piano tuition and there are many freely available video tutorials on the Internet. This study identified a set of challenging topics associated with learning jazz piano based on popular YouTube jazz piano tutorials. The results suggest that learners are struggling to understand the construction of complex chords in the 12 keys. Most tutorial videos show two parallel keyboards, one physical with the real hands and one virtual keyboard, which the viewers must map onto their own keyboard. Based on these results a series of visualization approaches were explored through a low-fi prototype by augmenting the physical piano keyboard with voicing instructions using a projector.

show abstract

Piano Genie

Cited by 23 publications

References 9 publications

Deep Learning for Audio Signal Processing

Deep Learning for Audio Signal Processing

A Review of Recent Deep Learning Approaches in Human-Centered Machine Learning

Enhanced Learning of Jazz Chords with a Projector Based Piano Keyboard Augmentation

Contact Info

Product

Resources

About