pages/1_History of Speech Recognition.py

import streamlit as st
from utils.levels import complete_level, render_page, initialize_level
from utils.login import initialize_login

LEVEL = 1

initialize_login()
initialize_level()


def step_page():
    st.header("History of Speech Recognition")
    st.markdown(
        """
    The history of speech recognition dates back several decades, and it's interesting to see how this technology has evolved over time. Let's take a journey through its key milestones:

    1. Early Attempts
    In the 1950s and 1960s, scientists began exploring the idea of using computers to understand human speech. One of the first notable systems was IBM's "Audrey" in 1952, which could recognize single spoken digits. However, these early attempts were limited by the technology available at the time, and accurate speech recognition remained a significant challenge."""
    )
    st.image(
        "https://www.beyonddesign.com/wp-content/uploads/2018/09/blog1.jpg.webp",
        use_column_width=True,
    )
    st.markdown(
        """
    2. Introduction of Hidden Markov Models (HMMs)
    In the 1970s and 1980s, researchers made significant progress in speech recognition by adopting Hidden Markov Models (HMMs). HMMs allowed for the modeling of speech sounds and their transitions, enabling more accurate recognition of spoken words and phrases. This breakthrough laid the foundation for many subsequent advancements.

    3. The DARPA Challenge
    In the 1980s and 1990s, the U.S. Defense Advanced Research Projects Agency (DARPA) initiated a series of speech recognition challenges to promote research in the field. These challenges played a crucial role in advancing the state of speech recognition technology. Notable milestones include the DARPA Speech Understanding Research (SUR) and the Resource Management (RM) evaluations.

    4. The Rise of Neural Networks
    In the 2000s, neural networks reemerged as a powerful tool for speech recognition. Deep learning, a subfield of machine learning, revolutionized the accuracy and performance of speech recognition systems. Neural networks allowed for the automatic extraction of features from speech data, making it easier to recognize and understand spoken language.

    5. Voice Assistants and Commercial Applications
    With the widespread adoption of smartphones and the Internet, speech recognition became a fundamental component of voice assistants. Apple's Siri, introduced in 2011, and subsequent voice assistants like Amazon's Alexa and Google Assistant, brought speech recognition to millions of users worldwide. These voice assistants could understand natural language commands, answer questions, and perform tasks based on spoken instructions.

    6. Ongoing Advancements
    In recent years, advancements in deep learning and the availability of large-scale datasets have further improved speech recognition accuracy. State-of-the-art models, such as OpenAI's Whisper, have achieved remarkable levels of performance, enabling applications in transcription services, call centers, language translation, and more."""
    )
    st.image(
        "https://www.gosmar.eu/machinelearning/wp-content/uploads/2020/05/cnn_img_480-1.png",
        use_column_width=True,
    )
    st.markdown(
        """The history of speech recognition is a testament to the persistence and innovation of researchers and scientists in overcoming challenges. As technology continues to progress, we can expect further improvements in accuracy, speed, and usability, opening up exciting possibilities for the future of speech recognition."""
    )

    st.info("Click on the button below to continue!")

    if st.button("Complete"):
        complete_level(LEVEL)


render_page(step_page, LEVEL)