Exploration and optimization of noise reduction algorithms for speech recognition in embedded devices:
Gespeichert in:
1. Verfasser: | |
---|---|
Format: | Abschlussarbeit Buch |
Sprache: | German |
Veröffentlicht: |
Aachen
Shaker
2009
|
Schriftenreihe: | Berichte aus der Informationstechnik
|
Schlagworte: | |
Online-Zugang: | Inhaltsverzeichnis |
Beschreibung: | XIV, 167 S. graph. Darst. 210 mm x 148 mm, 279 gr. |
ISBN: | 9783832282080 |
Internformat
MARC
LEADER | 00000nam a2200000 c 4500 | ||
---|---|---|---|
001 | BV035562892 | ||
003 | DE-604 | ||
005 | 00000000000000.0 | ||
007 | t | ||
008 | 090615s2009 gw d||| m||| 00||| ger d | ||
015 | |a 09,N25,0020 |2 dnb | ||
016 | 7 | |a 99453583X |2 DE-101 | |
020 | |a 9783832282080 |c PB. : EUR 48.80, EUR 48.80 (AT), sfr 97.60 (freier Pr.) |9 978-3-8322-8208-0 | ||
024 | 3 | |a 9783832282080 | |
035 | |a (OCoLC)423780381 | ||
035 | |a (DE-599)DNB99453583X | ||
040 | |a DE-604 |b ger |e rakddb | ||
041 | 0 | |a ger | |
044 | |a gw |c XA-DE-NW | ||
049 | |a DE-706 |a DE-83 | ||
082 | 0 | |a 621.3994 |2 22/ger | |
082 | 0 | |a 006.454 |2 22/ger | |
084 | |a ZN 6070 |0 (DE-625)157501: |2 rvk | ||
084 | |a 004 |2 sdnb | ||
100 | 1 | |a Setiawan, Panji |d 1977- |e Verfasser |0 (DE-588)138413541 |4 aut | |
245 | 1 | 0 | |a Exploration and optimization of noise reduction algorithms for speech recognition in embedded devices |c Panji Setiawan |
264 | 1 | |a Aachen |b Shaker |c 2009 | |
300 | |a XIV, 167 S. |b graph. Darst. |c 210 mm x 148 mm, 279 gr. | ||
336 | |b txt |2 rdacontent | ||
337 | |b n |2 rdamedia | ||
338 | |b nc |2 rdacarrier | ||
490 | 0 | |a Berichte aus der Informationstechnik | |
502 | |a Zugl.: Neubiberg, Univ. der Bundeswehr München, Diss., 2009 | ||
650 | 4 | |a Automatische Spracherkennung - Geräuschminderung - Frequenzbereich - Hidden-Markov-Modell | |
650 | 0 | 7 | |a Automatische Spracherkennung |0 (DE-588)4003961-4 |2 gnd |9 rswk-swf |
650 | 0 | 7 | |a Frequenzbereich |0 (DE-588)4155398-6 |2 gnd |9 rswk-swf |
650 | 0 | 7 | |a Geräuschminderung |0 (DE-588)4129292-3 |2 gnd |9 rswk-swf |
650 | 0 | 7 | |a Hidden-Markov-Modell |0 (DE-588)4352479-5 |2 gnd |9 rswk-swf |
655 | 7 | |0 (DE-588)4113937-9 |a Hochschulschrift |2 gnd-content | |
689 | 0 | 0 | |a Automatische Spracherkennung |0 (DE-588)4003961-4 |D s |
689 | 0 | 1 | |a Geräuschminderung |0 (DE-588)4129292-3 |D s |
689 | 0 | 2 | |a Frequenzbereich |0 (DE-588)4155398-6 |D s |
689 | 0 | 3 | |a Hidden-Markov-Modell |0 (DE-588)4352479-5 |D s |
689 | 0 | |5 DE-604 | |
856 | 4 | 2 | |m DNB Datenaustausch |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=017618600&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
999 | |a oai:aleph.bib-bvb.de:BVB01-017618600 |
Datensatz im Suchindex
_version_ | 1804139213086523392 |
---|---|
adam_text | CONTENTS SUMMARY I ACKNOWLEDGMENT III 1 INTRODUCTION 1 1.1 OBJECTIVES
AND MAIN ACHIEVEMENTS 7 1.2 THESIS OUTLINE 8 2 STOCHASTIC SPEECH
RECOGNITION 11 2.1 HIDDEN MARKOV MODEL (HMM) PARAMETER FORMULATION 15
2.2 THE HMM PARAMETER TRAINING 17 2.3 THE HMM RECOGNITION 19 2.4 THE
PROBLEM OF MISMATCH 21 2.5 A SURVEY OF ROBUSTNESS IN SPEECH RECOGNITION
23 3 SPEECH RECOGNITION SYSTEM DESCRIPTION AND EVALUATION 27 3.1 ETSI
DISTRIBUTED SPEECH RECOGNITION (DSR) FRONT-END 27 3.2 FRONT-END AND
BACK-END SYSTEM DESCRIPTION 29 3.2.1 SIEMENS FRONT-END (SFE) 29 3.2.2
SIEMENS BACK-END (SBE) 34 3.3 FRONT-END MODULE EXTENSIONS 34 3.3.1
ROOT-CEPSTRAL COEFFICIENTS 35 3.3.2 CEPSTRAL SMOOTHING 36 V
BIBLIOGRAFISCHE INFORMATIONEN HTTP://D-NB.INFO/99453583X DIGITALISIERT
DURCH VI CONTENTS 3.4 PERFORMANCE EVALUATION 36 3.5 DATABASES AND TASKS
37 3.5.1 AURORA 3 GERMAN 37 3.5.2 SPEECHDAT-CAR SPANISH 37 3.5.3 SPEECON
SPANISH 38 3.6 SYSTEM REQUIREMENTS IN EMBEDDED DEVICES 39 4 FREQUENCY
DOMAIN NOISE REDUCTION 41 4.1 NOISE ESTIMATION TECHNIQUES 44 4.1.1
THREE-STATE VOICE ACTIVITY DRIVEN NOISE PSD ESTIMATION 44 4.1.2 MINIMUM
STATISTICS NOISE PSD ESTIMATION 45 4.2 STATE-OF-THE-ART STSA ESTIMATORS
47 4.2.1 SPECTRAL SUBTRACTION 47 4.2.2 WIENER FILTERING 52 4.2.3
GAUSSIAN MODEL AND EPHRAIM-MALAH ESTIMATOR 54 4.2.4 LEAST-SQUARES
AMPLITUDE ESTIMATOR 58 4.2.5 TWO-STAGE MEL-WARPED WIENER FILTER 60 4.3
LEAST-SQUARES BASED WEIGHTING RULES 62 4.3.1 BATCH LEAST-SQUARES
FORMULATION IN THE FREQUENCY DOMAIN 63 4.3.2 RECURSIVE GAIN
LEAST-SQUARES 66 4.4 PARAMETER OPTIMIZATION: A MULTIDIMENSIONAL
OPTIMIZATION TASK 68 5 THE CONCEPT OF ENTROPY FOR FEATURE VECTOR
ANALYSIS 71 5. 1 UNCERTAINTY BOUNDS OF THE BAYES PROBABILITY OF ERROR 73
5.2 ESTIMATING H(Q) 74 5.3 APPROXIMATIONS TO THE MUTUAL INFORMATION
I(X;Q) 76 5.4 APPROXIMATION TO H( Q) 78 5.5 APPROXIMATION TO//(X) 80
5.5.1 MONOGRAM APPROXIMATION 81 5.5.2 BIGRAM APPROXIMATION 82 5.5.
CONTENTS VII 5.6.1 MONOGRAM APPROXIMATION ONE-DIMENSIONAL EXAMPLE 86
5.6.2 BIGRAM APPROXIMATION OF A 2-DIMENSIONAL EXAMPLE 90 5.7 INFLUENCE
OF NOISE ON THE FEATURE VECTORS 92 6 FRONT-END OPTIMIZATION AND
EVALUATION ON THE AURORA 3 GERMAN DIGITS DATABASE 95 6.1 EXPERIMENT I:
AFE AND SFE EXPERIMENTAL SETUPS ON THE SBE 95 6.1.1 ETSI ADVANCED
FRONT-END 95 6.1.2 SIEMENS FRONT-END 97 6.2 EXPERIMENT II:
INVESTIGATIONS ON THE AFE COMPONENTS 98 6.2.1 EFFECTS OF THE AFE
COMPONENTS COMBINED WITH THE BLIND EQUALIZATION (BE) TECHNIQUE 99 6.2.2
EFFECTS OF THE AFE COMPONENTS COMBINED WITH THE MAXIMUM LIKELI- HOOD
CHANNEL COMPENSATION (MLCC) TECHNIQUE 100 6.3 EXPERIMENT III: WEIGHTING
RULE EVALUATIONS 101 6.3.1 USING THE THREE-STATE VOICE ACTIVITY DRIVEN
NOISE PSD ESTIMATOR . ... 102 6.3.2 USING THE MINIMUM STATISTICS NOISE
PSD ESTIMATOR 103 6.4 EXPERIMENT IV: ROOT-CEPSTRAL COEFFICIENTS 105
6.4.1 USING THE THREE-STATE VOICE ACTIVITY DRIVEN NOISE PSD ESTIMATOR .
... 105 6.4.2 USING THE MINIMUM STATISTICS NOISE PSD ESTIMATOR 106 6.5
EXPERIMENT V: CEPSTRAL SMOOTHING 107 6.5.1 USING THE THREE-STATE VOICE
ACTIVITY DRIVEN NOISE PSD ESTIMATOR . ... 108 6.5.2 USING MINIMUM
STATISTICS NOISE PSD ESTIMATOR 110 7 NOISE REDUCTION EVALUATION ON THE
SPEECON AND SPEECHDAT-CAR SPANISH 113 7.1 SYSTEM OPTIMIZATION FOR THE
11.025 KHZ DATABASE 114 7.2 PERFORMANCE EVALUATION 115 8 VIII CONTENTS 9
CONCLUSIONS AND FUTURE DIRECTIONS 133 A HMM PARAMETER ESTIMATION 135 A.I
THE FORWARD-BACKWARD ALGORITHM 135 A.2 THE BAUM-WELCH ALGORITHM 136 B A
LOWER BOUND ON THE BAYES PROBABILITY OF ERROR 141 C WORKING WITH ENTROPY
143 C.I DIFFERENTIAL ENTROPY OF A ONE-DIMENSIONAL FEATURE VECTOR 143 C.2
DIFFERENTIAL ENTROPY OF A MULTIDIMENSIONAL FEATURE VECTOR 144 C.3
ENTROPY OF A MIXED DISTRIBUTION 145 C.4 ENTROPY OF A MONOMODAL GAUSSIAN
DISTRIBUTION 146 C.5 MARGINAL DISTRIBUTION OF THE FEATURE VECTOR 147 D
MODELING THE TEMPORAL STATISTICAL DEPENDENCY OF THE FEATURE VECTOR 149
BIBLIOGRAPHY 153
|
any_adam_object | 1 |
author | Setiawan, Panji 1977- |
author_GND | (DE-588)138413541 |
author_facet | Setiawan, Panji 1977- |
author_role | aut |
author_sort | Setiawan, Panji 1977- |
author_variant | p s ps |
building | Verbundindex |
bvnumber | BV035562892 |
classification_rvk | ZN 6070 |
ctrlnum | (OCoLC)423780381 (DE-599)DNB99453583X |
dewey-full | 621.3994 006.454 |
dewey-hundreds | 600 - Technology (Applied sciences) 000 - Computer science, information, general works |
dewey-ones | 621 - Applied physics 006 - Special computer methods |
dewey-raw | 621.3994 006.454 |
dewey-search | 621.3994 006.454 |
dewey-sort | 3621.3994 |
dewey-tens | 620 - Engineering and allied operations 000 - Computer science, information, general works |
discipline | Informatik Elektrotechnik / Elektronik / Nachrichtentechnik |
format | Thesis Book |
fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>02240nam a2200517 c 4500</leader><controlfield tag="001">BV035562892</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">00000000000000.0</controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">090615s2009 gw d||| m||| 00||| ger d</controlfield><datafield tag="015" ind1=" " ind2=" "><subfield code="a">09,N25,0020</subfield><subfield code="2">dnb</subfield></datafield><datafield tag="016" ind1="7" ind2=" "><subfield code="a">99453583X</subfield><subfield code="2">DE-101</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9783832282080</subfield><subfield code="c">PB. : EUR 48.80, EUR 48.80 (AT), sfr 97.60 (freier Pr.)</subfield><subfield code="9">978-3-8322-8208-0</subfield></datafield><datafield tag="024" ind1="3" ind2=" "><subfield code="a">9783832282080</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)423780381</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DNB99453583X</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rakddb</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">ger</subfield></datafield><datafield tag="044" ind1=" " ind2=" "><subfield code="a">gw</subfield><subfield code="c">XA-DE-NW</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-706</subfield><subfield code="a">DE-83</subfield></datafield><datafield tag="082" ind1="0" ind2=" "><subfield code="a">621.3994</subfield><subfield code="2">22/ger</subfield></datafield><datafield tag="082" ind1="0" ind2=" "><subfield code="a">006.454</subfield><subfield code="2">22/ger</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ZN 6070</subfield><subfield code="0">(DE-625)157501:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">004</subfield><subfield code="2">sdnb</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Setiawan, Panji</subfield><subfield code="d">1977-</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)138413541</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Exploration and optimization of noise reduction algorithms for speech recognition in embedded devices</subfield><subfield code="c">Panji Setiawan</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Aachen</subfield><subfield code="b">Shaker</subfield><subfield code="c">2009</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">XIV, 167 S.</subfield><subfield code="b">graph. Darst.</subfield><subfield code="c">210 mm x 148 mm, 279 gr.</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="490" ind1="0" ind2=" "><subfield code="a">Berichte aus der Informationstechnik</subfield></datafield><datafield tag="502" ind1=" " ind2=" "><subfield code="a">Zugl.: Neubiberg, Univ. der Bundeswehr München, Diss., 2009</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Automatische Spracherkennung - Geräuschminderung - Frequenzbereich - Hidden-Markov-Modell</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Automatische Spracherkennung</subfield><subfield code="0">(DE-588)4003961-4</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Frequenzbereich</subfield><subfield code="0">(DE-588)4155398-6</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Geräuschminderung</subfield><subfield code="0">(DE-588)4129292-3</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Hidden-Markov-Modell</subfield><subfield code="0">(DE-588)4352479-5</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</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="689" ind1="0" ind2="0"><subfield code="a">Automatische Spracherkennung</subfield><subfield code="0">(DE-588)4003961-4</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><subfield code="a">Geräuschminderung</subfield><subfield code="0">(DE-588)4129292-3</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="2"><subfield code="a">Frequenzbereich</subfield><subfield code="0">(DE-588)4155398-6</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="3"><subfield code="a">Hidden-Markov-Modell</subfield><subfield code="0">(DE-588)4352479-5</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">DNB Datenaustausch</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=017618600&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:BVB01-017618600</subfield></datafield></record></collection> |
genre | (DE-588)4113937-9 Hochschulschrift gnd-content |
genre_facet | Hochschulschrift |
id | DE-604.BV035562892 |
illustrated | Illustrated |
indexdate | 2024-07-09T21:40:30Z |
institution | BVB |
isbn | 9783832282080 |
language | German |
oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-017618600 |
oclc_num | 423780381 |
open_access_boolean | |
owner | DE-706 DE-83 |
owner_facet | DE-706 DE-83 |
physical | XIV, 167 S. graph. Darst. 210 mm x 148 mm, 279 gr. |
publishDate | 2009 |
publishDateSearch | 2009 |
publishDateSort | 2009 |
publisher | Shaker |
record_format | marc |
series2 | Berichte aus der Informationstechnik |
spelling | Setiawan, Panji 1977- Verfasser (DE-588)138413541 aut Exploration and optimization of noise reduction algorithms for speech recognition in embedded devices Panji Setiawan Aachen Shaker 2009 XIV, 167 S. graph. Darst. 210 mm x 148 mm, 279 gr. txt rdacontent n rdamedia nc rdacarrier Berichte aus der Informationstechnik Zugl.: Neubiberg, Univ. der Bundeswehr München, Diss., 2009 Automatische Spracherkennung - Geräuschminderung - Frequenzbereich - Hidden-Markov-Modell Automatische Spracherkennung (DE-588)4003961-4 gnd rswk-swf Frequenzbereich (DE-588)4155398-6 gnd rswk-swf Geräuschminderung (DE-588)4129292-3 gnd rswk-swf Hidden-Markov-Modell (DE-588)4352479-5 gnd rswk-swf (DE-588)4113937-9 Hochschulschrift gnd-content Automatische Spracherkennung (DE-588)4003961-4 s Geräuschminderung (DE-588)4129292-3 s Frequenzbereich (DE-588)4155398-6 s Hidden-Markov-Modell (DE-588)4352479-5 s DE-604 DNB Datenaustausch application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=017618600&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis |
spellingShingle | Setiawan, Panji 1977- Exploration and optimization of noise reduction algorithms for speech recognition in embedded devices Automatische Spracherkennung - Geräuschminderung - Frequenzbereich - Hidden-Markov-Modell Automatische Spracherkennung (DE-588)4003961-4 gnd Frequenzbereich (DE-588)4155398-6 gnd Geräuschminderung (DE-588)4129292-3 gnd Hidden-Markov-Modell (DE-588)4352479-5 gnd |
subject_GND | (DE-588)4003961-4 (DE-588)4155398-6 (DE-588)4129292-3 (DE-588)4352479-5 (DE-588)4113937-9 |
title | Exploration and optimization of noise reduction algorithms for speech recognition in embedded devices |
title_auth | Exploration and optimization of noise reduction algorithms for speech recognition in embedded devices |
title_exact_search | Exploration and optimization of noise reduction algorithms for speech recognition in embedded devices |
title_full | Exploration and optimization of noise reduction algorithms for speech recognition in embedded devices Panji Setiawan |
title_fullStr | Exploration and optimization of noise reduction algorithms for speech recognition in embedded devices Panji Setiawan |
title_full_unstemmed | Exploration and optimization of noise reduction algorithms for speech recognition in embedded devices Panji Setiawan |
title_short | Exploration and optimization of noise reduction algorithms for speech recognition in embedded devices |
title_sort | exploration and optimization of noise reduction algorithms for speech recognition in embedded devices |
topic | Automatische Spracherkennung - Geräuschminderung - Frequenzbereich - Hidden-Markov-Modell Automatische Spracherkennung (DE-588)4003961-4 gnd Frequenzbereich (DE-588)4155398-6 gnd Geräuschminderung (DE-588)4129292-3 gnd Hidden-Markov-Modell (DE-588)4352479-5 gnd |
topic_facet | Automatische Spracherkennung - Geräuschminderung - Frequenzbereich - Hidden-Markov-Modell Automatische Spracherkennung Frequenzbereich Geräuschminderung Hidden-Markov-Modell Hochschulschrift |
url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=017618600&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
work_keys_str_mv | AT setiawanpanji explorationandoptimizationofnoisereductionalgorithmsforspeechrecognitioninembeddeddevices |