Scribd
Upload
4 views7 pages

Lecture

The document discusses speech recognition as a key component of speech processing systems, which also include natural language processing and speech synthesis. It outlines the steps for visualizing audio signals using Python, including recording and sampling, and details applications for generating monotone audio signals and recognizing spoken words with the Google Speech API. The lecture concludes with a preview of the next topic, Natural Language Processing (NLP).

Uploaded by

hilolooztrk
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
4 views7 pages

Lecture

The document discusses speech recognition as a key component of speech processing systems, which also include natural language processing and speech synthesis. It outlines the steps for visualizing audio signals using Python, including recording and sampling, and details applications for generating monotone audio signals and recognizing spoken words with the Google Speech API. The lecture concludes with a preview of the next topic, Natural Language Processing (NLP).

Uploaded by

hilolooztrk
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 7

MIS4311

Machine Learning Applications

Spring 2024
Lecture #10
Speech Recognition
Speech processing system has mainly three tasks:

❖ speech recognition that allows the machine to catch the words,


phrases and sentences we speak

❖ Natural language processing to allow the machine to understand


what we speak

❖ Speech synthesis to allow the machine to speak.

We will focus on speech recognition that is the process of


understanding the words that are spoken by human beings.

Speech Recognition or Automatic Speech Recognition (ASR) is the


center of attention for AI projects like robotics.
Visualizing Audio Signals with Python
Two steps:

Recording
When you have to read the audio signal from a file, then record it
using a microphone, at first. (You can download the sample.wav file
from bulut.marmara.edu.tr)

Sampling
When recording with microphone, the signals are stored in a
digitized form. But to work upon it, the machine needs them in the
discrete numeric form. Hence, we should perform sampling at a
certain frequency and convert the signal into the discrete
numerical form. Choosing the high frequency for sampling implies
that when humans listen to the signal, they feel it as a continuous
audio signal.
Visualizing Audio Signals with Python
We show a stepwise approach to analyze an audio signal, using
Python, which is stored in a file.

Display the parameters like sampling frequency of the audio signal,


data type of signal and its duration.

Visualize the audio signal.


Generating Monotone Audio Signal
with Python
In the second application we generate the audio signal with some
predefined parameters and save the audio signal in an output file.

We define these parameters as:


duration = 4 # in seconds
frequency_sampling = 44100 #in hertz
frequency_tone = 784
Recognition of Spoken Words with
Python
In the third application we recognize the speech via michrophone.
Speech recognition means that when humans are speaking, a machine
understands it.
Here we are using Google Speech API in Python to make it happen.

We need to install the following packages:

conda install -c conda-forge SpeechRecognition #for sound recognition


conda install -c conda-forge gTTS #to use Google Translate API
conda install -c conda-forge Playsound #to play sound
conda install -c conda-forge PyAudio #for sound input and output
Next Week

❖ Natural Language Processing (NLP)

Thank you for your participation ☺

You might also like