Emotion recognition in speech using vocal landmarks:
Gespeichert in:
1. Verfasser: | |
---|---|
Format: | Abschlussarbeit Buch |
Sprache: | English |
Veröffentlicht: |
Passau
2017
|
Schlagworte: | |
Online-Zugang: | Inhaltsverzeichnis |
Beschreibung: | 76 Seiten Diagramme |
Internformat
MARC
LEADER | 00000nam a2200000 c 4500 | ||
---|---|---|---|
001 | BV044453083 | ||
003 | DE-604 | ||
005 | 00000000000000.0 | ||
007 | t | ||
008 | 170818s2017 |||| m||| 00||| eng d | ||
035 | |a (OCoLC)1159384663 | ||
035 | |a (DE-599)BVBBV044453083 | ||
040 | |a DE-604 |b ger |e rda | ||
041 | 0 | |a eng | |
049 | |a DE-739 | ||
100 | 1 | |a Wendlinger, Lorenz |e Verfasser |4 aut | |
245 | 1 | 0 | |a Emotion recognition in speech using vocal landmarks |c von Lorenz Wendlinger |
264 | 1 | |a Passau |c 2017 | |
300 | |a 76 Seiten |b Diagramme | ||
336 | |b txt |2 rdacontent | ||
337 | |b n |2 rdamedia | ||
338 | |b nc |2 rdacarrier | ||
502 | |b Bachelorarbeit |c Universität Passau |d 2017 | ||
655 | 7 | |0 (DE-588)4113937-9 |a Hochschulschrift |2 gnd-content | |
856 | 4 | 2 | |m Digitalisierung UB Passau - ADAM Catalogue Enrichment |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=029853948&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
999 | |a oai:aleph.bib-bvb.de:BVB01-029853948 |
Datensatz im Suchindex
_version_ | 1804177770581852160 |
---|---|
adam_text | Contents
1 Introduction 1
1.1 Emotion Representation.......................................... 2
2 Machine Learning 4
2.1 Fundamentals.................................................... 5
2.2 Challenges...................................................... 7
2.2.1 Feature Selection......................................... 7
2.2.2 Hyper parameter Optimization.............................. 7
2.2.3 Overfitting............................................... 8
2.3 Dimensionality Reduction........................... 9
2.3.1 Bag of Features........................................... 9
3 State of the Art 11
3.1 Features....................................................... 12
3.1.1 Mel Frequency Cepstral Coefficients...................... 12
3.1.2 Acoustic Landmarks....................................... 15
3.1.2.1 voiced / unvoiced............................... 15
3.1.2.2 p-center........................................ 16
3.1.2.3 Reduced Energy Cumulating ...................... 18
3.1.3 Formants ................................................ 18
3.2 Bag of Audio Words ............................................ 20
3.2.1 Codebook Generation ................................. 20
3.2.1.1 Clustering...................................... 20
3.2.1.2 Random Sampling................................. 22
3.2.1.3 Nonnegative Matrix Factorization................ 22
3.3 Classification ............................... 24
3.3.1 k-Nearest Neighbors ..................................... 24
3.3.2 Support Vector Machines.................................. 24
3.3.2.1 Linear SVM...................................... 24
3.3.2.2 Nonlinear SVM and the Kernel Trick.............. 26
3.3.2.3 e - Support Vector Regression................... 28
3.3.3 Random Forests........................................... 30
3.3.3.1 Decision Tree Construction...................... 30
3.4 Postprocessing................................................. 31
4 Task and Dataset
32
5 Experiments and Results 34
5.1 Methodology ................................................ 35
5.1.1 Process Flow......................................... 35
5.1.2 Loss Function........................................ 35
5.2 Preprocessing............................................... 39
5.3 Featuresets ................................................ 41
5.3.1 Acoustic Landmarks................................... 41
5.3.2 Low Level Descriptors................................ 43
5.4 Functionals................................................. 44
5.5 BoAW........................................................ 45
5.5.1 Codebook Generation ................................. 45
5.5.1.1 Clustering Methods .......................... 46
5.5.1.2 Nonnegative Matrix Factorization............. 50
5.6 Classification.............................................. 53
5.6.1 SVM.................................................. 53
5.6.2 Random Forests....................................... 54
5.6.3 k-Nearest Neighbors ................................. 56
5.7 Postprocessing.............................................. 57
5.8 Fusion...................................................... 58
5.8.1 Early Fusion......................................... 58
5.8.2 Late Fusion.......................................... 60
5.9 On Implementation........................................... 62
6 Conclusion and Outlook 63
6.1 Evaluation.................................................. 63
6.2 Future Work................................................. 64
Appendices 65
A Supplementary Information 66
B References 71
C Declaration of Authorship 76
|
any_adam_object | 1 |
author | Wendlinger, Lorenz |
author_facet | Wendlinger, Lorenz |
author_role | aut |
author_sort | Wendlinger, Lorenz |
author_variant | l w lw |
building | Verbundindex |
bvnumber | BV044453083 |
ctrlnum | (OCoLC)1159384663 (DE-599)BVBBV044453083 |
format | Thesis Book |
fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01069nam a2200277 c 4500</leader><controlfield tag="001">BV044453083</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">00000000000000.0</controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">170818s2017 |||| m||| 00||| eng d</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)1159384663</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV044453083</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-739</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Wendlinger, Lorenz</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Emotion recognition in speech using vocal landmarks</subfield><subfield code="c">von Lorenz Wendlinger</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Passau</subfield><subfield code="c">2017</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">76 Seiten</subfield><subfield code="b">Diagramme</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="502" ind1=" " ind2=" "><subfield code="b">Bachelorarbeit</subfield><subfield code="c">Universität Passau</subfield><subfield code="d">2017</subfield></datafield><datafield tag="655" ind1=" " ind2="7"><subfield code="0">(DE-588)4113937-9</subfield><subfield code="a">Hochschulschrift</subfield><subfield code="2">gnd-content</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">Digitalisierung UB Passau - ADAM Catalogue Enrichment</subfield><subfield code="q">application/pdf</subfield><subfield code="u">http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=029853948&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Inhaltsverzeichnis</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-029853948</subfield></datafield></record></collection> |
genre | (DE-588)4113937-9 Hochschulschrift gnd-content |
genre_facet | Hochschulschrift |
id | DE-604.BV044453083 |
illustrated | Not Illustrated |
indexdate | 2024-07-10T07:53:21Z |
institution | BVB |
language | English |
oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-029853948 |
oclc_num | 1159384663 |
open_access_boolean | |
owner | DE-739 |
owner_facet | DE-739 |
physical | 76 Seiten Diagramme |
publishDate | 2017 |
publishDateSearch | 2017 |
publishDateSort | 2017 |
record_format | marc |
spelling | Wendlinger, Lorenz Verfasser aut Emotion recognition in speech using vocal landmarks von Lorenz Wendlinger Passau 2017 76 Seiten Diagramme txt rdacontent n rdamedia nc rdacarrier Bachelorarbeit Universität Passau 2017 (DE-588)4113937-9 Hochschulschrift gnd-content Digitalisierung UB Passau - ADAM Catalogue Enrichment application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=029853948&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis |
spellingShingle | Wendlinger, Lorenz Emotion recognition in speech using vocal landmarks |
subject_GND | (DE-588)4113937-9 |
title | Emotion recognition in speech using vocal landmarks |
title_auth | Emotion recognition in speech using vocal landmarks |
title_exact_search | Emotion recognition in speech using vocal landmarks |
title_full | Emotion recognition in speech using vocal landmarks von Lorenz Wendlinger |
title_fullStr | Emotion recognition in speech using vocal landmarks von Lorenz Wendlinger |
title_full_unstemmed | Emotion recognition in speech using vocal landmarks von Lorenz Wendlinger |
title_short | Emotion recognition in speech using vocal landmarks |
title_sort | emotion recognition in speech using vocal landmarks |
topic_facet | Hochschulschrift |
url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=029853948&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
work_keys_str_mv | AT wendlingerlorenz emotionrecognitioninspeechusingvocallandmarks |