Audio data

The kind of data used in the algorithm implementation for generating metal music

Directly or indirectly, we are always in contact with audio. Your brain is continuously processing and understanding audio data and giving you information about the environment. A simple example can be your conversations with people which you do daily. This speech is discerned by the other person to carry on the discussions. Even when you think you are in a quiet environment, you tend to catch much more subtle sounds, like the rustling of leaves or the splatter of rain. This is the extent of your connection with audio.

There are devices built which help you catch these sounds and represent it in computer readable format. Examples of these formats are

• wav (Waveform Audio File) format

• mp3 (MPEG-1 Audio Layer 3) format

• WMA (Windows Media Audio) format

• MIDI(Musical Instrument Digital Interface)

If you give a thought on what an audio looks like, it is nothing but a wave like format of data, where the amplitude of audio change with respect to time. This can be pictorial represented as follows.

An audio signal

Applications of Audio Processing

• Indexing music collections according to their audio features

• Recommending music for radio channels

• Similarity search for audio files

• Speech processing and synthesis – generating artificial voice for conversational agents

Dataset

The training data is around 100 MIDI files of metal songs of the band “Iron Maiden” (MIDI is a format that directly encodes musical notes). To keep it simple, we won’t label them with emotions, our output will be another metal melody, just like our training files.

MIDI (Musical Instrument Digital Interface)

MIDI (Musical Instrument Digital Interface) is a protocol designed for recording and playing back music on digital synthesizers that is supported by many makes of personal computer sound cards. Originally intended to control one keyboard from another, it was quickly adopted for the personal computer. Rather than representing musical sound directly, it transmits information about how music is produced. The command set includes note-ons, note-offs, key velocity, pitch bend and other methods of controlling a synthesizer. The sound waves produced are those already stored in a wavetable in the receiving instrument or sound card.

Perhaps the best way to understand what MIDI is to first understand what it is not:

· MIDI isn't music

· MIDI doesn't contain any actual sounds

· MIDI isn't a digital music file format like MP3 or WAV

MIDI is nothing more than data -- a set of instructions. MIDI data contains a list of events or messages that tell an electronic device (musical instrument, computer sound card, cell phone, et cetera) how to generate a certain sound.

MIDI signal