Audio Signal Processing Basics

Audio data

• Audio data represents analog sounds in a digital form, preserving the main properties of
the original. As we know from school lessons in physics, a sound is a wave of vibrations
traveling through a medium like air or water and finally reaching our ears.

• It has three key characteristics to be considered when analyzing audio data — time period,
amplitude, and frequency.

Audio data file formats

• WAV or WAVE (Waveform Audio File Format)

• AIFF (Audio Interchange File Format)

• FLAC (Free Lossless Audio Codec)

• MP3

Audio signals

• Audio signals are signals that vibrate in the audible frequency range. When someone talks,
it generates air pressure signals; the ear takes in these air pressure differences and
communicates with the brain.

• That's how the brain helps a person recognize that the signal is speech and understand what
someone is saying.

• There are a lot of MATLAB tools to perform audio processing, but not as many exist in
Python.

Some data features and transformations that are important in speech and audio processing are
Spectrum and cepstrum

• Spectrum and cepstrum are two particularly important features in audio processing.

• Mathematically, a spectrum is the Fourier transform of a signal. A Fourier transform

converts a time-domain signal to the frequency domain.

• In other words, a spectrum is the frequency domain representation of the input audio's time-
domain signal.

• A cepstrum is formed by taking the log magnitude of the spectrum followed by an inverse
Fourier transform.
 • This results in a signal that's neither in the frequency domain (because we took an inverse
Fourier transform) nor in the time domain (because we took the log magnitude prior to the
inverse Fourier transform).

• The domain of the resulting signal is called the quefrency.

Audio analysis

• Audio analysis is a process of transforming, exploring, and interpreting audio signals

recorded by digital devices.

• Aiming at understanding sound data, it applies a range of technologies, including state-of-

the-art deep learning algorithms.

• Audio analysis has already gained broad adoption in various industries, from entertainment
to healthcare to manufacturing.

• Example for audio analysis Speech recognition,Voice recognition,Music recognition and

Environmental sound recognition

Audio data analysis steps

• Obtain project-specific audio data stored in standard file formats.

• Prepare data for your machine learning project, using software tools

• Extract audio features from visual representations of sound data.

 • Select the machine learning model and train it on audio features.

Audio analysis software

• Audacity

• Tensorflow-io package

• Librosa

• Audio Toolbox by MathWorks

****************************************************************************

FEATURES DOES MIR TOOLBOX HAVE

• In short, the MIR toolbox allows us to extract data about musical features dealing
with waveform and spectral analysis, tonality, pitch, dynamics, rhythm, tempo,
timbre, and other high-level audio features.

MIRtoolbox offers an integrated set of functions written in Matlab, dedicated to the

extraction from audio files of musical features such as tonality, rhythm, structures, etc.

*********************************************8

TOOLBOXES ARE THERE IN MATLAB

• Access MATLAB Add-On Toolboxes

• Statistics and Machine Learning Toolbox™ (Statistics and Machine Learning Toolbox)

• Curve Fitting Toolbox™ (Curve Fitting Toolbox)

• Control System Toolbox™ (Control System Toolbox)

• Signal Processing Toolbox™ (Signal Processing Toolbox)

• Mapping Toolbox™ (Mapping Toolbox)

The toolbox is available free of charge under the GNU General Public License Auditory toolbox,
Netlab toolbox, SOM toolbox, MIRtoolbox requires Matlab version 7 and Mathworks' Signal
Processing toolbox.
How does voice processing work?

• Voice recognition software on computers requires analog audio to be converted

into digital signals, known as analog-to-digital (A/D) conversion.

• For a computer to decipher a signal, it must have a digital database of words or syllables
as well as a quick process for comparing this data to signals.

• The speech patterns are stored on the hard drive and loaded into memory when the program
is running.

• A comparator checks these stored patterns against the output of the A/D converter -- an
action called pattern recognition.

*****************************************************************8
 APPLICATIONS IN REAL WORLD IN SHIPPING INDUSTRY
The shipping industry plays a crucial role in global trade and commerce, and there are several
applications of technology that are being used to optimize shipping operations and improve
efficiency. Here are some examples:

1. Electronic Data Interchange (EDI): EDI is a computer-to-computer exchange of business

documents between companies. In the shipping industry, EDI is used to exchange data such as
bills of lading, invoices, and shipping manifests between shippers, carriers, and freight forwarders.
This streamlines the documentation process and reduces the risk of errors and delays.
2. Automated Port Management Systems: Automated port management systems use sensors,
cameras, and other technologies to monitor and control port operations. These systems can
optimize the movement of cargo and vessels, reduce congestion, and improve safety.
3. Global Positioning Systems (GPS): GPS technology is widely used in the shipping industry to
track the location of vessels and cargo. This information is used to optimize shipping routes,
improve efficiency, and ensure that cargo is delivered on time.
4. Internet of Things (IoT): The IoT involves the use of sensors and other devices to collect data and
transmit it over the internet. In the shipping industry, IoT technology is being used to monitor
cargo conditions (such as temperature and humidity) in real-time, as well as to track the location
of containers and vessels.
5. Blockchain: Blockchain technology provides a secure and transparent way to record and verify
transactions. In the shipping industry, blockchain is being used to create secure digital records of
shipping documents, such as bills of lading and customs declarations. This can help reduce fraud
and errors, and streamline the documentation process.
6. Artificial Intelligence (AI): AI technology is being used in the shipping industry to analyze data
and make predictions about vessel movements, weather conditions, and other factors that can
impact shipping operations. This can help companies optimize shipping routes, reduce costs, and
improve efficiency.

7. Autonomous ships: With advances in computer vision, machine learning, and other AI
technologies, it is becoming increasingly possible to develop autonomous ships. These
ships could potentially reduce human error, lower operational costs, and improve safety.
 8. Predictive maintenance: AI can be used to predict when equipment is likely to fail, allowing
for preemptive maintenance and reducing the likelihood of costly breakdowns.
9. Supply chain optimization: AI can analyze data from various sources, such as weather
reports, port schedules, and vessel tracking, to optimize supply chain operations. This could
lead to more efficient cargo routing, better inventory management, and reduced shipping
times.
10. Improved navigation: AI can help ships navigate more efficiently by analyzing factors such
as sea conditions, vessel speed, and fuel consumption. This could reduce fuel costs and
improve environmental sustainability.
11. Cargo monitoring: AI can monitor cargo conditions, such as temperature, humidity, and
vibration, in real-time. This could help ensure that cargo is delivered in optimal condition
and reduce losses due to damage or spoilage.
************************************************************************

KNOWLEDGE-BASED SYSTEM

 A knowledge-based system (KBS) is a type of computer system that analyzes knowledge,

data and other information from sources to generate new knowledge.
 It uses AI concepts to solve problems, which may be useful for assisting with human
learning and making decisions.
 These systems often have built-in problem-solving capabilities that allow them to
understand the context of the data that they review and process and make informed
decisions based on the knowledge that they store

Knowledge-based systems typically have three components, which include:

1. A knowledge base

2. An inference engine

3. A user interface

Types of knowledge-based systems

Case-based systems

Case-based systems use case-based reasoning. This involves reviewing past knowledge of similar
situations. Based on what it finds, the knowledge-based system provides solutions that were
effective in those given situations.

Expert systems

Expert systems are one of the most common types of knowledge-based systems. These systems
mimic human experts' decision-making processes, making them helpful for complex analyses,
calculations and predictions. In addition to presenting solutions, they provide specific explanations
for the problems they're solving.

Hypertext manipulation systems

Hypertext manipulation systems store knowledge by linking text to other texts and by using
hypertext. Hypertext refers to a network of discrete blocks of information interconnected as a way
to store data. This type of system allows you to access many types of data easily.

Intelligent tutoring systems

Intelligent tutoring systems are knowledge-based systems specifically designed to support

learning. These systems provide users with personalized feedback and instructions based on their
performance and inquiries. As such, they're often used in education, allowing students to learn
more and have a personalized learning experience without direct intervention from a teacher.

Rule-based systems

Rule-based systems rely on human-made, hard-coded rules. It uses these rules to analyze and
manipulate data to achieve specific outcomes. This may involve using IF-THEN rules, which
establish that if a user makes a certain request, then the system delivers a certain outcome.

Knowledge-based system work

• A knowledge-based system is a computer system that uses artificial intelligence techniques
to store and retrieve knowledge.
• The system is designed to solve problems by applying knowledge to a specific problem
domain.
• The system stores knowledge in the form of rules, which are then used to generate solutions
to specific problems. The rules are typically written in a formal language, which allows the
system to reason about the knowledge and apply it to new situations.
• The system's ability to reason about the knowledge is what allows it to generate new
solutions to problems. The system can also learn new knowledge by observing how humans
solve problems

• Knowledge-based systems also include an interface through which users query the system
and interact with it.
• Some systems encode expert knowledge as rules and are therefore referred to as rule-based
systems.
• Another approach, case-based reasoning, substitutes cases for rules.
• Cases are essentially solutions to existing problems that a case-based system will attempt
to apply to a new problem.
 ******************************************************************0

DISTRIBUTED ARTIFICIAL INTELLIGENCE

 Distributed Artificial Intelligence (DAI) is a subfield of Artificial Intelligence (AI) that

focuses on building intelligent systems that operate in a distributed manner, using multiple
agents to work together towards a common goal.
 DAI combines principles from various fields including computer science, economics,
mathematics, and psychology to create complex systems that can solve problems in a
distributed manner.

****************************************************************0

Benefits of using knowledge-based systems include:

 Accelerating delivery processes of goods and services for B2C organizations

 Assisting users in making expert decisions
 Creating new knowledge by reviewing existing data and stored knowledge
 Grouping data across different areas of expertise
 Handling significant amounts of structured and unstructured data intelligently and
efficiently
 Improving productivity and consistency with decision-making processes
 Integrating knowledge on a large scale to create a common platform for accessing
knowledge
 Providing efficient documentation of important data for users to access easily
 Serving as an expert resource with human experts are unavailable
 Storing data conveniently for future use

***********************************************************0

KNOWLEDGE-BASED SYSTEM

 A knowledge-based system (KBS) is a type of computer system that analyzes knowledge,

data and other information from sources to generate new knowledge.
  It uses AI concepts to solve problems, which may be useful for assisting with human
learning and making decisions.
 These systems often have built-in problem-solving capabilities that allow them to
understand the context of the data that they review and process and make informed
decisions based on the knowledge that they store.

A knowledge-based system is an artificial intelligence technology that uses expert knowledge to

solve problems or make decisions. Here are some examples of knowledge-based systems:

 Medical Diagnosis System

 Fraud Detection System
 Legal Expert System
 Decision Support System
 Intelligent Tutoring System.
 Planning and Scheduling System
 Customer Service System
 Quality Control System

************************************************************8