INFS1020 Project: AI-Driven Music Innovation and Design Thinking

This project delves into the innovative application of artificial intelligence in music creation. It proposes a device that allows users to listen to and interact with their favorite music, and even create their own tunes without instruments by humming creative music. The project outlines the device's functionality, including voice command and instrument selection, and analyzes its potential through SWOT and PESTLE analyses. It addresses implementation challenges, such as machine learning customization and sound quality, and incorporates design thinking principles like brainstorming and prototyping. The project explores the technical and societal impact of AI in music, emphasizing user experience and technological advancements. The project includes a paper prototype to validate the voice recognition and humming process. The conclusion highlights the potential of AI to enhance human-music interaction. References to relevant literature are also provided.

INNOVATION IN MUSIC
WITH ARTIFICIAL
INTELLIGENCE

INTRODUCTION…
 The innovation is regarding the use of artificial
intelligence in music.
 People would be able to listen and interact with the
device which would play their favorite music.
 With the contribution of technologies in various field,
it will be also important to create an innovation in
music as well.
 This innovation will be different from the existing
ones.
 People would be even able to create their own music
without using any musical instruments.

BACKGROUND…
 The device will be created by using artificial
intelligence.
 Along with listening to their favorite songs by
commanding with the voice, people would be able to
create their own tunes.
 They will require to hum their creative music and the
device will automatically create the tune with
enhanced clarity.
 The device will have the option of selecting any
musical instruments for creating the tunes.
 Users will have to select the options of instruments
and they will just hum the music.
 Then, the device would automatically create the tune
with the selected musical instruments.

SWOT..
Strength:
• Highly creative innovation
•Enhancement if musuc
listening experience
• Music can be created without
musical devices
Weakness:
• The cost would be high
• There could be difficulties on
recognizing the voice
Opportunities:
• Can be extremely popular among
music creators
• Can result in digital disruption
Threats:
• Risks of bugs
• Other security issues

PESTEL..
 Political: In terms if political impact, only trade
policies for supply of the resources for the devices
can be considered.
 Economic: This device would be economically
profitable for the users.
 Society: People would be highly interested for this
innovative device.
 Technology: AI and machine learning would enhance
the features of the device.
 Environment: There would be no environmental
impact while developing the device.
 Legal: All the legal policies need to be maintained
while developing the device.

PROBLEM STATEMENT…
 It would be challenging to input the tone of different
musical instruments in the device.
 Problems can occur if the device fails to recognize or
understand the humming or the tunes created by
voice.
 This can happen if the device fails to utilize the
machine learning capabilities
 It would be thus important to input high quality
machine learning capabilities in the device.
 Therefore; a significant research will be required to
do so effectively.

MIND MAP

IDEATION..
 It would be beneficial to install the tones of
maximum 5-6 instruments which are mostly used for
creating music.
 This would help in making the machine less
complicated.
 This idea would also help in reducing the congestion
that the machine learning technology can face while
creating the tunes of the music.
 Maximum 50 meters would be allowed from where
the voice of the users can be tracked by the device.
 The solutions have been ideated through
brainstorming
 The three above mentioned solutions have been
considered.

BRAINSTORMING..

PROTOTYPE…
 50 meters limit has been selected for recognizing
and understanding the voice clearly.
 The problem regarding the difficulties on
understanding the humming thus can be solved by
using this solution.
 Users will have to command the device or hum the
music within 50 meters
 Users will have to command and hum clearly without
other noise disturbances.
 Noise disturbances can result in difficulty for artificial
intelligence to understand the voice (Brynjolfsson
and Mcafee 2017).
 Noise disturbances can also result in error on
receiving the signal (Smith 2016).

JUSTIFICATION
 This prototype will be useful for clearing the way for
the device to recognize the voice.
 Only one person will be able to command the device
or hum the music at a time.
 This process would be useful for utilizing the device
with perfection.
 There would be no difficulties to even create tunes
from own creative music of the users.
 Even the music can be played a number of times
when the device will store the tunes in its memory.

IMPLEMENTATION ISSUE..
 The issues of implementation can occur in terms of
setting customization for each user.
 The device will automatically customize the music
playlists for the users.
 Moreover; it will also suggest some creative tunes
based on the previous tunes created by the
individual users.
 Therefore; it could be a challenge for the developers
to implement high quality machine learning
experience.
 Issue can also come regarding the quality of sounds.
 There needs to be clarity of the sounds created by
the machine.

PAPER PROTOTYPE..

CONCLUSION…
 This innovation is going to be challenging, however if
developed it can enhance the human and music
interaction.
 It will be important to implement all the necessary
features in the device that have been assessed.
 There should be provisions for the users to update the
system whenever necessary.
 It will help in adding more features of artificial
intelligence in the device.

REFERENCES..
 Brynjolfsson, E. and Mcafee, A.N.D.R.E.W 2017, The
business of artificial intelligence. Harvard Business
Review.
 Połap, D 2016, September. Neuro-heuristic voice
recognition. In 2016 Federated Conference on
Computer Science and Information Systems
(FedCSIS) (pp. 487-490). IEEE.
 Smith, E 2016, Fuzzy Logic and Speech Recognition
Applications on Autonomous Vehicles.