Uni ed Acoustic Modeling using Deep Conditional Random Fields
Journal Title: Transactions on Machine Learning and Artificial Intelligence - Year 2015, Vol 3, Issue 2
Abstract
Acoustic models based on Deep Neural Networks (DNNs) lead to sig- ni cant improvement in the recognition accuracy. In these methods, Hid- den Markov Models (HMMs) state scores are computed using exible dis- criminant DNNs. On the other hand, Conditional Random Fields (CRFs) are undirected graphical models that maintain the Markov properties of HMMs formulated using the maximum entropy (MaxEnt) principle. CRFs have limited ability to model spectral phenomena since they have single quadratic activation function per state. It is possible and natural to use DNNs to compute the state scores in CRFs. These acoustic models are known as Deep Conditional Random Fields (DCRFs). In this work, a variant of DCRFs is presented and connections with hybrid DNN/HMM systems are established. Under certain assumptions, both DCRFs and hybrid DNN/HMM systems can lead to exact same results for a phone recognition task. In addition, linear activation functions are used in the DCRFs output layer. Consequently, DCRFs and traditional DNN/HMM systems have the same decoding speed.
Authors and Affiliations
Yasser Hifny
Keywords
Related Articles
- EP ID EP278889
- DOI 10.41738/tmlai.32.1124
- Views 84
- Downloads 0
A Real Time Embedded System Architecture for Autonomous Underwater Sensors Localization
Underwater Acoustic Sensor Networks (UWASNs) consist of a variable number of autonomous sensors or vehicles that are deployed over a given area to perform smart sensing and collaborative monitoring tasks. In UWASNs, sens...
Combining Overall and Target Oriented Sentiment Analysis over Portuguese Text from Social Media
This document describes an approach to perform sentiment analysis on social media Portuguese content. In a single system, we perform polarity classification for both the overall sentiment, and target oriented sentiment....
A Comparative Study Between Operating Systems (Os) for the Internet of Things (IoT)
Abstract : We describe The Internet of Things (IoT) as a network of physical objects or "things" embedded with electronics, software, sensors, and network connectivity, which enables these objects to collect and exchange...
Creatinine, Urea and Uric Acid in Hospitalized Patients with and Without Hyperglycemia Analysis using Generalized Additive Model
Hyperglycemia is an important risk factor for heart disease and premature mortality. In hospitalized patients, it is related to an increase in morbidity and development of other disease like kidney disease. To evaluate t...
A Metaheuristic Procedure for Calculating Optimal Osmotic Dehydration Parameters: A Case Study of Mushrooms
The Firefly Algorithm (FA) metaheuristic is employed to determine the optimal parameter settings in a case study of the osmotic dehydration of mushrooms. In the case, the functional form of the dehydration model is estab...