NATIONAL UNIVERSITY OF SINGAPORE School of Computing PH.D DEFENCE - PUBLIC SEMINAR
ثبت نشده
چکیده
Automatic Speech Recognition (ASR) has been one of the most popular research areas in computer science. Many state-of-the-art ASR systems still use the Hidden Markov Model (HMM) for acoustic modelling due to its efficient training and decoding. HMM state output probability of an observation is assumed to be independent of the other states and the surrounding observations. Since temporal correlation between observations exists due to the nature of speech, this assumption is poorly made for speech signal. Although the use of the dynamic parameters and the Gaussian mixture models (GMM) has greatly improved the system performance, implicitly or explicitly modelling the trajectory temporal correlation can potentially improve the ASR systems.
منابع مشابه
NATIONAL UNIVERSITY OF SINGAPORE School of Computing PH.D DEFENCE - PUBLIC SEMINAR
This thesis aims to address a number of program reasoning problems faced every day by programmers, using the technique of symbolic execution. Symbolic execution has the advantage of avoiding "infeasible" paths in the program (paths that cannot be exercised for any input), exploring which could provide spurious information about the program and mislead the programmer. However, as symbolic execut...
متن کاملNational Health Service Principles as Experienced by Vulnerable London Migrants in “Austerity Britain”: A Qualitative Study of Rights, Entitlements, and Civil-Society Advocacy
Background Recent British National Health Service (NHS) reforms, in response to austerity and alleged ‘health tourism,’ could impose additional barriers to healthcare access for non-European Economic Area (EEA) migrants. This study explores policy reform challenges and implications, using excerpts from the perspectives of non-EEA migrants and health advocates in London. Methods A qualitative ...
متن کاملNATIONAL UNIVERSITY OF SINGAPORE School of Computing PH.D DEFENCE - PUBLIC SEMINAR
Mobile apps have become commonplace in society. But with millions of apps flooding the app stores, recommender systems have become indispensable tools as they help consumers overcome the problem of information overload. By sifting through the ocean of apps, they allow consumers to discover new and compelling apps through personalized recommendations. Yet, conventional recommender systems have t...
متن کاملNATIONAL UNIVERSITY OF SINGAPORE School of Computing PH.D DEFENCE - PUBLIC SEMINAR Title: Using Meta-Data from Free-Text User-Generated Content to Improve Personalized Recommendation by Reducing Sparsity Speaker: Mr
Recommender Systems (RS) have become increasingly essential in many domains for alleviating the "information overload" problem, but existing recommendation techniques suffer from the sparsity problem due to insufficient input data. In this thesis, we aim at extracting and incorporating meta-data from free-text UserGenerated Content (UGC) to lessen the effects of sparsity and therefore improve t...
متن کاملA framework for stakeholder oriented mindfulness: case of RFID implementation at YCH Group, Singapore
Department of Decision Sciences, School of Business, National University of Singapore, Singapore; Department of Information Systems, School of Computing, National University of Singapore, Singapore; Department of Operations Management and Information Technology, HEC School of Management, Paris; Department of Information and Decision Sciences, University of Illinois at Chicago, Chicago, IL, U.S....
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2014