Automatic detection of abnormal stress patterns in unit selection synthesis
نویسندگان
چکیده
This paper introduces a method to detect lexical stress errors in unit selection synthesis automatically using machine learning algorithms. If unintended stress patterns can be detected following unit selection, based on features available in the unit database, it may be possible to modify the units during waveform synthesis to correct errors and produce an acceptable stress pattern. In this paper, three machine learning algorithms were trained with acoustic measurements from natural utterances and corresponding stress patterns: CART, SVM and MaxEnt. Our experimental results showed that MaxEnt performs the best (83.3% for 3-syllable words, 88.7% for 4-syllable words correctly classified) in the natural stress pattern classification. Though classification rates are good, a large number of false alarms are produced. However, there is some indication that signal modifications based on false positives do little harm to the speech output.
منابع مشابه
Automatic Prostate Cancer Segmentation Using Kinetic Analysis in Dynamic Contrast-Enhanced MRI
Background: Dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) provides functional information on the microcirculation in tissues by analyzing the enhancement kinetics which can be used as biomarkers for prostate lesions detection and characterization.Objective: The purpose of this study is to investigate spatiotemporal patterns of tumors by extracting semi-quantitative as well as w...
متن کاملThe Effectiveness of the Automatic System of Fuzzy Logic-Based Technical Patterns Recognition: Evidence from Tehran Stock Exchange
The present research proposes an automatic system based on moving average (MA) and fuzzy logic to recognize technical analysis patterns including head and shoulder patterns, triangle patterns and broadening patterns in the Tehran Stock Exchange. The automatic system was used on 38 indicators of Tehran Stock Exchange within the period 2014-2017 in order to evaluate the effectiveness of technical...
متن کاملA study of lexical stress patterns in unit selection synthesis
In this paper we describe a method that detects and remedies lexical stress errors in unit selection synthesis automatically using machine learning algorithms. If unintended stress patterns can be detected following unit selection, based on features available in the unit database, it may be possible to modify the units during waveform synthesis to correct errors and produce an acceptable stress...
متن کاملTumor Detection and Morphology Assessment in the Liver Tissue Using an Automatic Tactile Robot
In this paper an automatic examination robot was developed to improve the process of cancer detection, tumor localization and geometrical shape diagnosis. A uniformly distributed compressive load was applied to the top tissue surface and the resultant mechanical stress was measured that was employed for the tumor diagnosis task. The experimental examinations were performed on the soft tissue of...
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 2010