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
Considerations for Real-time Streaming ASR
Was this section helpful?
- Sequence Transduction with Recurrent Neural Networks, Alex Graves, 2012 International Conference of Machine Learning (ICML) 2012 Workshop on Representation Learning DOI: 10.48550/arXiv.1211.3711 - This foundational paper introduces the Recurrent Neural Network-Transducer (RNN-T), a key architecture for streaming ASR due to its ability to emit outputs step-by-step without waiting for the full input sequence.
- Robust Voice Activity Detection Using Deep Neural Networks, Xiang Zhang, S. M. Ahadi, V. Ramana Rao, T. J. Cox, 2013 Interspeech 2013 (ISCA (International Speech Communication Association)) DOI: 10.21437/Interspeech.2013-402 - This paper explores the use of Deep Neural Networks for Voice Activity Detection, a component for efficient real-time streaming ASR systems to manage computational resources and utterance boundaries.
- Deep Learning in Spoken Language Processing: From Speech Recognition to Text-to-Speech, Li Deng, Xiao Li, 2019 (Academic Press) DOI: 10.1016/C2016-0-03004-7 - This book provides a comprehensive overview of deep learning techniques applied to spoken language processing, including discussions on various ASR architectures and their practical considerations relevant to both offline and streaming modes.