All Courses

Applied Speech Recognition

Chapter 1: Foundations of Digital Audio and Speech

Introduction to Automatic Speech Recognition Systems

Properties of Human Speech: Phonemes and Allophones

Digital Audio Signals: Sampling, Quantization, and Encoding

Working with Audio Data in Python using Librosa

Time and Frequency Domain Analysis

Introduction to Spectrograms for Speech Visualization

Hands-on Practical: Loading and Visualizing Audio Waveforms

Chapter 2: Feature Extraction for Speech Recognition

The Role of Feature Extraction in ASR

Mel Frequency Cepstral Coefficients (MFCCs)

Calculating MFCCs Step-by-Step

Filter Banks and Log-Mel Spectrograms

Feature Normalization Techniques

Comparing MFCCs and Spectrograms as Input Features

Practice: Extracting and Normalizing Features from a Dataset

Chapter 3: Acoustic Modeling with Deep Neural Networks

Overview of Acoustic Models in ASR

Building Acoustic Models with Recurrent Neural Networks

Addressing Sequential Challenges with LSTMs and GRUs

Connectionist Temporal Classification (CTC) Loss

Implementing a CTC-based ASR Model

Hands-on Practical: Training a Simple LSTM Acoustic Model with CTC

Chapter 4: Advanced Acoustic Models and Architectures

Attention Mechanisms for Speech Recognition

Sequence-to-Sequence (Seq2Seq) Models for ASR

Listen, Attend, and Spell (LAS) Architecture

Introduction to Transformer Models for ASR

Conformer: Combining CNNs and Transformers

An Overview of Pre-trained ASR Models

Practice: Fine-tuning a Pre-trained ASR Model

Chapter 5: Language Modeling and Decoding

The Function of Language Models in ASR

N-gram Language Models

Building an N-gram Model with KenLM

Decoding Graphs for Model Integration

Decoding Algorithms: Greedy Search vs Beam Search

Implementing Beam Search with a Language Model

Hands-on Practical: Integrating a Language Model into a CTC Decoder

Chapter 6: Evaluating and Deploying ASR Systems

Metrics for ASR Performance: WER and CER

Calculating Word Error Rate

Common Data Augmentation Techniques for Speech

Using Hugging Face Pipelines for ASR

Building a Speech-to-Text Application with Gradio

Considerations for Real-time Streaming ASR

Practice: Evaluating and Building a Demo Application

Applied Speech Recognition

This course provides a comprehensive guide to building and implementing automatic speech recognition (ASR) systems. It covers the complete workflow, starting from audio signal processing and feature extraction to constructing and training modern deep learning models. Participants will work with contemporary tools and architectures, such as LSTMs, Transformers, and Connectionist Temporal Classification (CTC) loss, to build functional speech-to-text pipelines. The material is designed for engineers and developers with a foundation in machine learning who want to develop practical skills in the speech technology domain.

Prerequisites Python & ML foundation

Level:

Intermediate

Audio Preprocessing
Preprocess and prepare audio data for ASR models.
Feature Extraction
Implement feature extraction techniques like MFCCs and Log-Mel Spectrograms.
Acoustic Modeling
Build and train acoustic models using RNNs, LSTMs, and Transformers.
Language Modeling
Integrate language models into the decoding process for improved accuracy.
System Evaluation
Evaluate and benchmark ASR system performance using standard metrics like WER.
Deployment
Construct a functional speech-to-text application pipeline.

There are no prerequisite courses for this course.

There are no recommended next courses at the moment.

Login to Write a Review

Share your feedback to help other learners.

© 2026 ApX Machine LearningEngineered with