THE ALGORITHM OF MAXIMUM MUTUAL INFORMATION FOR MODEL FITTING AND SPECTRUM ESTIMATION

1987 ◽  
pp. 397-400
Keyword(s):  
Mutual Information ◽  
Model Fitting ◽  
Spectrum Estimation ◽  
Maximum Mutual Information

The maximum mutual information without coding for binary quantum-state signals

1998 ◽  
Vol 45 (2) ◽  
pp. 269-282 ◽  
Author(s):  
MASAO OSAKI, OSAMU HIROTA MASASHI BAN
Keyword(s):  
Mutual Information ◽  
Quantum State ◽  
Maximum Mutual Information

Human Action Detection Based on Tracking Region of Maximum Mutual Information

2012 ◽  
Vol 38 (12) ◽  
pp. 2023 ◽  
Author(s):  
Tai-Qing WANG ◽  
Sheng-Jin WANG ◽  
Xiao-Qing DING
Keyword(s):  
Mutual Information ◽  
Human Action ◽  
Action Detection ◽  
Human Action Detection ◽  
Maximum Mutual Information

Maximum mutual information SPLICE transform for seen and unseen conditions

2005 ◽  
Author(s):  
Jasha Droppo ◽  
Alex Acero
Keyword(s):  
Mutual Information ◽  
Maximum Mutual Information

Semi-supervised maximum mutual information training of deep neural network acoustic models

2015 ◽  
Author(s):  
Vimal Manohar ◽  
Daniel Povey ◽  
Sanjeev Khudanpur
Keyword(s):  
Neural Network ◽  
Mutual Information ◽  
Deep Neural Network ◽  
Acoustic Models ◽  
Maximum Mutual Information

scholarly journals Prosodic Feature-Based Discriminatively Trained Low Resource Speech Recognition System

2022 ◽  
Vol 14 (2) ◽  
pp. 614
Author(s):  
Taniya Hasija ◽  
Virender Kadyan ◽  
Kalpna Guleria ◽  
Abdullah Alharbi ◽  
Hashem Alyami ◽  
...  
Keyword(s):  
Speech Recognition ◽  
Mutual Information ◽  
Data Augmentation ◽  
Recognition System ◽  
Speech Recognition System ◽  
Prosodic Features ◽  
Prosodic Feature ◽  
Feature Based ◽  
Maximum Mutual Information ◽  
Children's Speech

Speech recognition has been an active field of research in the last few decades since it facilitates better human–computer interaction. Native language automatic speech recognition (ASR) systems are still underdeveloped. Punjabi ASR systems are in their infancy stage because most research has been conducted only on adult speech systems; however, less work has been performed on Punjabi children’s ASR systems. This research aimed to build a prosodic feature-based automatic children speech recognition system using discriminative modeling techniques. The corpus of Punjabi children’s speech has various runtime challenges, such as acoustic variations with varying speakers’ ages. Efforts were made to implement out-domain data augmentation to overcome such issues using Tacotron-based text to a speech synthesizer. The prosodic features were extracted from Punjabi children’s speech corpus, then particular prosodic features were coupled with Mel Frequency Cepstral Coefficient (MFCC) features before being submitted to an ASR framework. The system modeling process investigated various approaches, which included Maximum Mutual Information (MMI), Boosted Maximum Mutual Information (bMMI), and feature-based Maximum Mutual Information (fMMI). The out-domain data augmentation was performed to enhance the corpus. After that, prosodic features were also extracted from the extended corpus, and experiments were conducted on both individual and integrated prosodic-based acoustic features. It was observed that the fMMI technique exhibited 20% to 25% relative improvement in word error rate compared with MMI and bMMI techniques. Further, it was enhanced using an augmented dataset and hybrid front-end features (MFCC + POV + Fo + Voice quality) with a relative improvement of 13% compared with the earlier baseline system.

Constrained maximum mutual information dimensionality reduction for language identification

2012 ◽  
Author(s):  
Shuai Huang ◽  
Glen A. Coppersmith ◽  
Damianos Karakos
Keyword(s):  
Mutual Information ◽  
Dimensionality Reduction ◽  
Language Identification ◽  
Maximum Mutual Information
Sign in / Sign up

Export Citation Format

Share Document