Multilingual Representations for Low-Resource Speech Processing
Explore multilingual speech representations to reduce data requirements for new language speech recognition systems, focusing on low-resource scenarios and keyword search performance.
Imputer - Sequence Modelling via Imputation and Dynamic Programming
Explore a novel sequence-to-sequence model that balances efficiency and performance using imputation and dynamic programming for faster inference in various applications.
Learning How to Learn Efficiently - Nando de Freitas, DeepMind
Explore efficient learning techniques for neural networks to solve multiple tasks with limited data, focusing on developing adaptable "prior" networks for rapid task-specific learning.
Speech Recognition and Graph Transformer Networks
Explore modern speech recognition techniques, including connectionist temporal classification, beam search decoding, and Graph Transformer Networks, with expert insights and practical applications.
Hidden Markov Models
Learn about Hidden Markov Models, their applications in speech recognition and robotics, and key algorithms like the Forward Algorithm in this comprehensive overview.
Partially Observable Reinforcement Learning
Explore partially observable reinforcement learning, covering Markov processes, hidden models, and recurrent neural networks for decision-making in uncertain environments.
Deep Learning Applications by Rina Panigrahy
Explore deep learning applications, from basic concepts to advanced techniques. Learn about neural networks, optimization methods, and real-world uses in image and speech recognition.
OpenAI Whisper - Translate and Transcribe Your Video and Audio at Command Line
Comprehensive walkthrough of OpenAI Whisper for multilingual speech recognition, translation, and transcription using command-line interface, with practical demonstrations across various audio formats.
Hands-On Tutorial to Use Hindi on Android for Typing and Speech to Text
Learn to use Hindi on Android for typing and speech-to-text, with tips for optimal results and content management using Google Drive and Docs. Ideal for creating literature and poetry on mobile devices.
Conversational AI with Jarvis - Checking Out the API
Explore NVIDIA Jarvis API for end-to-end conversational AI, including text-to-speech, speech-to-text, and named entity recognition. Learn installation, setup, and practical applications.
Deep Learning with Neural Networks and TensorFlow Introduction
Introduction to deep learning with neural networks, covering theory, models, optimization, and TensorFlow. Explore biologically-inspired machine learning techniques and their evolution in the field of artificial intelligence.
TinyML - Using Machine Learning on Microcontrollers to Recognize Speech
Learn to implement speech recognition on microcontrollers using TinyML. Train a neural network, convert it to TensorFlow Lite, and deploy it on an ARM board for real-time wake word detection.
Speech-to-Intent on MCU: TinyML for Efficient Device Control - Lecture 6
Learn efficient speech-to-intent techniques for MCUs, focusing on direct parsing of user utterances into actionable output. Explore model training, deployment, and testing on Wio Terminal.
Applied Deep Learning in Speech Recognition and Collaborative Filtering - Session 5
Explore cutting-edge AI applications in speech recognition and collaborative filtering systems, featuring NVIDIA Research insights from NeurIPS 2018.
On-Device Neural End-to-End Speech Recognition and Synthesis Algorithms - A Review
Comprehensive review of on-device neural speech recognition and synthesis algorithms, exploring end-to-end models, optimization techniques, and their potential for on-device implementation.
Structured Quantization for Neural Network Language Model Compression
探讨神经网络语言模型的结构化量化压缩技术,展示如何在不损失性能的情况下实现70-100倍的高压缩率,适用于资源受限场景。
Speech Recognition on Low Power Devices
Explore multilingual speech recognition on low-power devices, covering model optimization techniques, neural network compression, and practical demonstrations for efficient implementation.
From Small to Tiny: Co-designing ML Models, Computational Precision, and Circuits - Energy-Accuracy Trade-offs
Explore co-designing ML models, computational precision, and circuits for energy-efficient tinyML systems. Learn about cross-layer optimization and cascaded networks for embedded applications.
Ultra-Low-Power Command Recognition for Ubiquitous Devices
Explore ultra-low-power command recognition for ubiquitous devices, covering noise challenges, system goals, core functions, training, and implementation on tiny hardware.
Build Your Own AI Assistant - Creating a Voice-Activated System
Learn to create your own AI assistant using Python and Raspberry Pi. Covers architecture, hardware/software setup, and implementation of key features like speech recognition and natural language processing.
tinyML: Impact and Growth of Always-On Devices
Explore the growing impact of tinyML devices in everyday life, from always-on voice in phones to environmental sensing in machines, and learn about the market's rapid expansion and technological requirements.