The Tempo 2 Algorithm: Adjusting Time-Delays By Supervised Learning
نویسندگان
چکیده
In this work we describe a new method that adjusts time-delays and the widths of time-windows in artificial neural networks automatically. The input of the units are weighted by a gaussian input-window over time which allows the learning rules for the delays and widths to be derived in the same way as it is used for the weights. Our results on a phoneme classification task compare well with results obtained with the TDNN by Waibel et al., which was manually optimized for the same task.
منابع مشابه
دسته‌بندی داده‌های دورده‌ای با ابرمستطیل موازی محورهای مختصات
One of the machine learning tasks is supervised learning. In supervised learning we infer a function from labeled training data. The goal of supervised learning algorithms is learning a good hypothesis that minimizes the sum of the errors. A wide range of supervised algorithms is available such as decision tress, SVM, and KNN methods. In this paper we focus on decision tree algorithms. When we ...
متن کاملA Post-Processing Procedure for Improving Music Tempo Estimates Using Supervised Learning
Tempo estimation is a fundamental problem in music information retrieval and has been researched extensively. One problem still unsolved is the tendency of tempo estimation algorithms to produce results that are wrong by a small number of known factors (so-called octave errors). We propose a method that uses supervised learning to predict such tempo estimation errors. In a post-processing step,...
متن کاملTemplate-Based Estimation of Tempo: Using Unsupervised or Supervised Learning to create better spectral templates
Observation probability • Probability to observe Yo(fk,tm) given tempo bi and RST mj 1) Compute the Yo(l,tm,bi) corresponding to the assumption bi 2) Select the mj which have a reference tempo Bj close to bi: (abs(log2(bi/Bj))<0.3785 3) Compute the one-minus cosine distance between Yo(l,tm,b) and mj=Yj(l) Template-Based Estimation of Tempo: Using Unsupervised or Supervised Learning to create be...
متن کاملAn Evolutionary Strategy for Supervised Training of Biologically Plausible Neural Networks
Spiking neural networks represent a more plausible model of real biological neurons. In contrast to the classical artificial neural networks, which adopt a high abstraction of real neurons, spiking neurons consider time as an important feature for information representation and processing. However, good training algorithms are needed for better exploitation of these realistic models. Most exist...
متن کاملCiteSeer: An Autonomous Web Agent for Automatic Retrieval and Identification of Interesting Publications
Many connectionist approaches to musical expectancy and music composition let the question of ``Whatnext?'' overshadow the equally important question of ``When next?''. One cannot escape the latter question, one oftemporal structure, when considering the perception of musical meter. We view the perception of metrical structure asa dynamic process where the temporal organization of e...
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 1990