YoVDO

UBM-based Acoustic Modeling for ASR - 2009

Offered By: Center for Language & Speech Processing(CLSP), JHU via YouTube

Tags

Speech Recognition Courses Machine Learning Courses Signal Processing Courses Hidden Markov Models Courses Feature Extraction Courses Gaussian Mixture Models Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore advanced techniques in acoustic modeling for Automatic Speech Recognition (ASR) in this comprehensive lecture by Daniel Povey from the Center for Language & Speech Processing at Johns Hopkins University. Delve into the intricacies of Universal Background Model (UBM) based approaches, understanding their application and benefits in improving ASR systems. Gain insights into state-of-the-art methodologies and research developments in the field of speech recognition as of 2009. Learn how UBM techniques can enhance the accuracy and efficiency of acoustic models, potentially leading to more robust and adaptable ASR systems. Suitable for researchers, engineers, and graduate students in speech technology and machine learning.

Syllabus

UBM based Acoustic Modeling for ASR (Daniel Povey) - 2009


Taught by

Center for Language & Speech Processing(CLSP), JHU

Related Courses

Cluster Analysis and Unsupervised Machine Learning in Python
Udemy
Unsupervised Learning
Serrano.Academy via YouTube
Hands on Machine Learning - Unsupervised Learning
Shashank Kalanithi via YouTube
PCA, AE, K-Means, Gaussian Mixture Model, Sparse Coding, and Intuitive VAE
Alfredo Canziani via YouTube
Small Covers for Near-zero Sets of Polynomials and Learning Latent Variable Models
IEEE via YouTube