Bachelor Thesis from the year 2014 in the subject Electrotechnology, grade: 1,0, University of Stuttgart (Institut für Signalverarbeitung und Systemtheorie), course: Elektrotechnik und Informationstechnik, language: English, abstract: This thesis deals with emotion recognition from speech signals using several featuresets and classifiers. Feature sets with different sizes are compared: the feature setof the Institute for Signal Processing and System Theory as well as standardisedfeature sets of eight paralinguistic challenges. The question is whether there is aconnection between the size of a feature set and the performance. The feature setsare investigated with SFFS and without in combination with Naive Bayes classifier,k-Nearest-Neighbour classifier and Support Vector Machine. The goal of this thesisis to find those features which are selected most commonly for good performance.Diese Arbeit befasst sich mit der Erkennung von Emotionen aus Sprachsignalen. Es werden verschiedene Merkmalsätze und Klassifizierer auf ihre Leistungsfähigkeit getestet. Dabei werden Merkmalsätze mit unterschiedlichen Größen verglichen: der Merkmalsatz vom Institut für Signalverarbeitung und Systemtheorie sowie standardisierte Merkmalsätze von acht Wettbewerben, in denen paralinguistische Informationen erkannt werden sollten. Die Frageist, ob es einen Zusammenhang zwischen der Größe eines Merkmalsatzes und der Leistungsfähigkeit gibt. Die Merkmalsätze werden sowie mit auch als ohne Merkmalsauswahl (SFFS) in Kombination mit dem Naiven Bayes Klassifizierer, k-Nächste-Nachbarn Klassifizierer und einer Support Vector Machine untersucht. Das Ziel dieser Arbeit ist, die Merkmale zu finden, die bei den besten Merkmalsätzen am häufigsten ausgewählt wurden.
Comparison of different features sets and classifiers for emotion recognition of speech
RRP:
$124.00
Description
Bachelor Thesis from the year 2014 in the subject Electrotechnology, grade: 1,0, University of Stuttgart (Institut für Signalverarbeitung und Systemtheorie), course: Elektrotechnik und Informationstechnik, language: English, abstract: This thesis deals with emotion recognition from speech signals using several featuresets and classifiers. Feature sets with different sizes are compared: the feature setof the Institute for Signal Processing and System Theory as well as standardisedfeature sets of eight paralinguistic challenges. The question is whether there is aconnection between the size of a feature set and the performance. The feature setsare investigated with SFFS and without in combination with Naive Bayes classifier,k-Nearest-Neighbour classifier and Support Vector Machine. The goal of this thesisis to find those features which are selected most commonly for good performance.Diese Arbeit befasst sich mit der Erkennung von Emotionen aus Sprachsignalen. Es werden verschiedene Merkmalsätze und Klassifizierer auf ihre Leistungsfähigkeit getestet. Dabei werden Merkmalsätze mit unterschiedlichen Größen verglichen: der Merkmalsatz vom Institut für Signalverarbeitung und Systemtheorie sowie standardisierte Merkmalsätze von acht Wettbewerben, in denen paralinguistische Informationen erkannt werden sollten. Die Frageist, ob es einen Zusammenhang zwischen der Größe eines Merkmalsatzes und der Leistungsfähigkeit gibt. Die Merkmalsätze werden sowie mit auch als ohne Merkmalsauswahl (SFFS) in Kombination mit dem Naiven Bayes Klassifizierer, k-Nächste-Nachbarn Klassifizierer und einer Support Vector Machine untersucht. Das Ziel dieser Arbeit ist, die Merkmale zu finden, die bei den besten Merkmalsätzen am häufigsten ausgewählt wurden.
In many cases, the way we say something tells more about our feelings and attitudes than what we actually say. This is especially true in emotional situations and...
Automatic speech recognition (ASR) involves the transformation of acoustic speech signal captured by a microphone, a telephone, or other transducers, into a text sequence. It is also known as the ...
This work has been selected by scholars as being culturally important, and is part of the knowledge base of civilization as we know it. This work was reproduced from the original artifact, and...
This is a reproduction of a book published before 1923. This book may have occasional imperfections such as missing or blurred pages, poor pictures,...
Discover your next great read at BookLoop, Australiand online bookstore offering a vast selection of titles across various genres and interests. Whether you're curious about what's trending or searching for graphic novels that captivate, thrilling crime and mystery fiction, or exhilarating action and adventure stories, our curated collections have something for every reader. Delve into imaginative fantasy worlds or explore the realms of science fiction that challenge the boundaries of reality. Fans of contemporary narratives will find compelling stories in our contemporary fiction section. Embark on epic journeys with our fantasy and science fiction titles,
Shop Trending Books and New Releases
Explore our new releases for the most recent additions in romance books, fantasy books, graphic novels, crime and mystery books, science fiction books as well as biographies, cookbooks, self help books, tarot cards, fortunetelling and much more. With titles covering current trends, booktok and bookstagram recommendations, and emerging authors, BookLoop remains your go-to local australian bookstore for buying books online across all book genres.
Shop Best Books By Collection
Stay updated with the literary world by browsing our trending books, featuring the latest bestsellers and critically acclaimed works. Explore titles from popular brands like Minecraft, Pokemon, Star Wars, Bluey, Lonely Planet, ABIA award winners, Peppa Pig, and our specialised collection of ADHD books. At BookLoop, we are committed to providing a diverse and enriching reading experience for all.
Sign In
your cart
Your cart is empty
Menu
Search
PRE-SALES
If you have any questions before making a purchase chat with our online operators to get more information.