Advanced Speech Recognition and Synthesis
Chapter 1: Foundations of Modern Speech Processing Pipelines
Advanced Audio Feature Extraction
Statistical Modeling Review for Speech
Deep Learning Architectures for Sequences
Components of ASR Systems
Components of TTS Systems
Evaluation Metrics Revisited
Chapter 2: Advanced Acoustic Modeling for ASR
Hybrid HMM-DNN Systems
Connectionist Temporal Classification (CTC)
Attention-Based Encoder-Decoder Models
RNN Transducer (RNN-T)
Transformer Architectures for ASR
Advanced Training Techniques
Decoding Algorithms Comparison
Hands-on Practical: Building an End-to-End ASR Model
Chapter 3: Language Modeling and Adaptation in ASR
Neural Language Models for ASR
Shallow Fusion and Deep Fusion
Contextual ASR
Speaker Adaptation Techniques
Environment and Channel Adaptation
Unsupervised and Semi-Supervised Learning for ASR
Multi-Lingual and Cross-Lingual ASR
Practice: Fine-tuning ASR with Adaptation Data
Chapter 4: Advanced Text-to-Speech Synthesis
Autoregressive Acoustic Models (Tacotron, Transformer TTS)
Non-Autoregressive Acoustic Models (FastSpeech, ParaNet)
Flow-Based Models for TTS
Generative Adversarial Networks (GANs) in TTS
Prosody Modeling and Control
Expressive Speech Synthesis
Voice Cloning and Conversion
Hands-on Practical: Training an Advanced TTS Model
Chapter 5: Neural Vocoders and Waveform Generation
Limitations of Traditional Vocoders
Autoregressive Waveform Models (WaveNet, WaveRNN)
Flow-Based Vocoders (WaveGlow, FloWaveNet)
GAN-Based Vocoders (MelGAN, HiFi-GAN)
Diffusion Models for Vocoding
Conditioning Neural Vocoders
Evaluation of Synthesized Audio Quality
Hands-on Practical: Using a Neural Vocoder
Chapter 6: Optimization, Deployment, and Toolkits
Model Quantization for Speech Models
Model Pruning and Sparsification
Knowledge Distillation for ASR/TTS
Optimized Inference Engines (ONNX Runtime, TensorRT)
Deployment Considerations for Streaming ASR
Deployment Considerations for Real-Time TTS
Overview of Speech Processing Toolkits (ESPnet, NeMo, Coqui)
Practice: Optimizing a Speech Model
Contextual ASR
Was this section helpful?
- Large-Scale Contextual Speech Recognition with a Recurrent Neural Network Language Model, Anjishnu Kumar, Ganesh Venkatesh, Kevin Kilgour, Taras Halych, Ruoming Pang, Bo Li, Ron Weiss, Jason Riesa, Pedro J. Moreno, 2018 Interspeech 2018 (International Speech Communication Association (ISCA)) DOI: 10.21437/Interspeech.2018-1241 - This paper presents a method for shallow fusion in contextual ASR by biasing a recurrent neural network language model with specific context lists.
- Contextual Listen, Attend and Spell, Etienne Bruguier, Olivier Siohan, Anjishnu Kumar, George Tucker, 2019 Interspeech 2019 (ISCA (International Speech Communication Association)) DOI: 10.21437/Interspeech.2019-1784 - This paper details the 'Contextual Listen, Attend and Spell (CLAS)' model, a specific neural approach to incorporating context into attention-based end-to-end ASR systems.
- Speech and Language Processing (3rd ed. draft), Daniel Jurafsky and James H. Martin, 2025 (Stanford University) - A comprehensive textbook providing a broad theoretical foundation for speech recognition, including language modeling concepts and adaptation strategies.