in Advances in Neural Information Processing Systems
نویسنده
چکیده
In this paper, we use mutual information to characterize the distributions of phonetic and speaker/channel information in a time-frequency space. The mutual information (MI) between the pho-netic label and one feature, and the joint mutual information (JMI) between the phonetic label and two or three features are estimated. The Miller's bias formulas for entropy and mutual information estimates are extended to include higher order terms. The MI and the JMI for speaker/channel recognition are also estimated. The results are complementary to those for phonetic classiication. Our results show how the phonetic information is locally spread and how the speaker/channel information is globally spread in time and frequency.
منابع مشابه
A DSS-Based Dynamic Programming for Finding Optimal Markets Using Neural Networks and Pricing
One of the substantial challenges in marketing efforts is determining optimal markets, specifically in market segmentation. The problem is more controversial in electronic commerce and electronic marketing. Consumer behaviour is influenced by different factors and thus varies in different time periods. These dynamic impacts lead to the uncertain behaviour of consumers and therefore harden the t...
متن کاملDesigning and implementing a system for Automatic recognition of Persian letters by Lip-reading using image processing methods
For many years, speech has been the most natural and efficient means of information exchange for human beings. With the advancement of technology and the prevalence of computer usage, the design and production of speech recognition systems have been considered by researchers. Among this, lip-reading techniques encountered with many challenges for speech recognition, that one of the challenges b...
متن کاملDamage detection and structural health monitoring of ST-37 plate using smart materials and signal processing by artificial neural networks
Structural health monitoring (SHM) systems operate online and test different materials using ultrasonic guided waves and piezoelectric smart materials. These systems are permanently installed on the structures and display information on the monitor screen. The user informs the engineers of the existing damage after observing signal loss which appears after damage is caused. In this paper health...
متن کاملImproving Phoneme Sequence Recognition using Phoneme Duration Information in DNN-HSMM
Improving phoneme recognition has attracted the attention of many researchers due to its applications in various fields of speech processing. Recent research achievements show that using deep neural network (DNN) in speech recognition systems significantly improves the performance of these systems. There are two phases in DNN-based phoneme recognition systems including training and testing. Mos...
متن کاملPersian Phone Recognition Using Acoustic Landmarks and Neural Network-based variability compensation methods
Speech recognition is a subfield of artificial intelligence that develops technologies to convert speech utterance into transcription. So far, various methods such as hidden Markov models and artificial neural networks have been used to develop speech recognition systems. In most of these systems, the speech signal frames are processed uniformly, while the information is not evenly distributed ...
متن کاملQuad-pixel edge detection using neural network
One of the most fundamental features of digital image and the basic steps in image processing, analysis, pattern recognition and computer vision is the edge of an image where the preciseness and reliability of its results will affect directly on the comprehension machine system made objective world. Several edge detectors have been developed in the past decades, although no single edge detector...
متن کامل