<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>3115</id>
    <completedYear>2025</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>100206</pageFirst>
    <pageLast/>
    <pageNumber>11</pageNumber>
    <edition/>
    <issue/>
    <volume>20</volume>
    <type>article</type>
    <publisherName>Elsevier</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>2025-10-15</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Neural network synthetic dataset generation for fault detection in district heating substations</title>
    <abstract language="eng">District heating systems (DHS) play a vital role in sustainable heating solutions and the decarbonization of the energy sector. However, inefficiencies due to undetected faults in substations result in high return temperatures, increasing heat losses, and limiting the integration of renewable energy sources. The lack of publicly available labeled datasets poses a significant challenge for fault detection using supervised learning models. To address this issue, this study explores three machine learning-based synthetic data generation techniques – time series forecasting, generative adversarial networks (GANs), and fault signature transfer.&#13;
These methods aim to increase publicly available data either by sharing the generating model or a synthetic dataset. The novelty lies in the combination of advanced supervised machine learning methods being applied to a large, fully labeled data set to create new, equally labeled data for publication, as, to our knowledge, no such dataset has been compiled before. We evaluate our methods on the first-of-its-kind ILSE dataset, which includes real-world smart meter data from 547 substations and 1,162 reviewed faults from a German DHS network, including detailed root cause information. Overall, time series forecasting achieves an MAPE of 3% to 10% for inlet and outlet temperature and 25% to 40% for heat load and flow rate, both of which are within year-to-year variance. For GANs, specifically TimeGAN, we found a discriminative score of about 0.10 compared to 0.24 in the original publication when tested on Energy benchmark data. Fault signature transfer has yet to yield usable results, most likely due to the high variance in the fault signatures, fault duration, and overlapping or multiple root causes. Finally, fault data in the synthetic data is not yet good enough for practical use, e.g. training a fault detector.</abstract>
    <parentTitle language="eng">Smart Energy</parentTitle>
    <identifier type="doi">10.1016/j.segy.2025.100206</identifier>
    <enrichment key="PeerReviewed">Ja</enrichment>
    <enrichment key="RS_Acronym">ILSE</enrichment>
    <enrichment key="RS_Correlation">Ja</enrichment>
    <enrichment key="RS_ProjectTitle">Intelligente lernende Systeme in Energieverbünden</enrichment>
    <enrichment key="RS_FundingAgency">BMWK</enrichment>
    <enrichment key="RS_GrantNumber">03EN3033</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Dominik Stecher</author>
    <author>Lukas Ziegltrum</author>
    <author>Paul Reiprich</author>
    <author>Christian Fuchs</author>
    <author>Andreas Maier</author>
    <author>Jochen Schmidt</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Synthetic fault generation</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Data augmentation</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>District heating</value>
    </subject>
    <collection role="ddc" number="05">Zeitschriften, fortlaufende Sammelwerke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>2798</id>
    <completedYear>2024</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>134016</pageFirst>
    <pageLast/>
    <pageNumber>13</pageNumber>
    <edition/>
    <issue/>
    <volume>313</volume>
    <type>article</type>
    <publisherName>Elsevier</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Creating a labelled district heating data set: From anomaly detection towards fault detection</title>
    <abstract language="eng">For an efficient operation of district heating systems, being able to detect anomalies and faults at an early stage is highly desirable. Here, data-driven machine learning methods can be a cornerstone, particularly for fault detection in district heating substations, where the availability of heat meter data keeps increasing. However, the creation of data sets suitable for training such machine learning models poses challenges to researchers and practitioners alike. To address this problem, we propose a systematic and domain-specific process for data set creation for fault detection in the form of practical guidelines. This process concretizes the data science and data mining cross-industry standard CRISP-DM for the district heating domain and focuses on the process steps of goal definition, data acquisition and understanding, and data curation. We aim to enable researchers and practitioners to create data sets for fault detection in the district heating domain and therefore also enable the creation or improvement of machine learning models in this domain. In addition, we propose a minimum viable feature set for fault detection in district heating networks with the goal of enabling better cooperation between researchers and easier transfer of the resulting machine learning models, to better proliferate new progress in the field.</abstract>
    <parentTitle language="eng">Energy</parentTitle>
    <identifier type="doi">10.1016/j.energy.2024.134016</identifier>
    <enrichment key="PeerReviewed">Ja</enrichment>
    <enrichment key="RS_Acronym">ILSE</enrichment>
    <enrichment key="RS_Correlation">Ja</enrichment>
    <enrichment key="RS_ProjectTitle">Intelligente Lernende Systeme in Energieverbünden</enrichment>
    <enrichment key="RS_FundingAgency">BMWK</enrichment>
    <enrichment key="RS_GrantNumber">03EN3033</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <author>Dominik Stecher</author>
    <author>Martin Neumayer</author>
    <author>Adithya Ramachandran</author>
    <author>Anastasia Hort</author>
    <author>Andreas Maier</author>
    <author>Dominikus Bücker</author>
    <author>Jochen Schmidt</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Machine Learning</value>
    </subject>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>2152</id>
    <completedYear>2023</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>127569</pageFirst>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume>276</volume>
    <type>article</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Fault and anomaly detection in district heating substations: A survey on methodology and data sets</title>
    <abstract language="eng">District heating systems are essential building blocks for affordable, low-carbon heat supply. Early detection and elimination of faults is crucial for the efficiency of these systems and necessary to achieve the low temperatures targeted for 4th generation district heating systems. Especially methods for fault and anomaly detection in district heating substations are currently of high interest, as faults in substations can be repaired quickly and inexpensively, and smart meter data are becoming widely available. In this paper, we review recent scientific publications presenting data-driven approaches for fault and anomaly detection in district heating substations with a focus on methods and data sets. Our review indicates that researchers use a wide variety of methods, mostly focusing on unsupervised anomaly detection rather than fault detection. This is due to a lack of labeled data sets, preventing the use of supervised learning methods and quantitative analysis. Together with the lack of publicly available data sets, this impedes the accurate comparison of individual methods. To overcome this impediment, increase the comparability of different methods and foster competition, future research should focus on establishing publicly available data sets, and industry-relevant metrics as benchmarks.</abstract>
    <parentTitle language="eng">Energy</parentTitle>
    <identifier type="doi">10.1016/j.energy.2023.127569</identifier>
    <enrichment key="PeerReviewed">Ja</enrichment>
    <enrichment key="RS_Acronym">ILSE</enrichment>
    <enrichment key="RS_Correlation">Ja</enrichment>
    <enrichment key="RS_ProjectTitle">Intelligente Lernende Systeme in Energieverbünden</enrichment>
    <enrichment key="RS_FundingAgency">BMWK</enrichment>
    <enrichment key="RS_GrantNumber">03EN3033</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <author>Martin Neumayer</author>
    <author>Dominik Stecher</author>
    <author>Sebastian Grimm</author>
    <author>Andreas Maier</author>
    <author>Dominikus Bücker</author>
    <author>Jochen Schmidt</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>District heating systems</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Fault/anomaly detection</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Machine learning</value>
    </subject>
    <collection role="ddc" number="05">Zeitschriften, fortlaufende Sammelwerke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <collection role="institutes" number="">Fakultät für Ingenieurwissenschaften</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>1837</id>
    <completedYear>2021</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>108</pageFirst>
    <pageLast>115</pageLast>
    <pageNumber>8</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Recurrence Plot Spacial Pyramid Pooling Network for Appliance Identification in Non-Intrusive Load Monitoring</title>
    <abstract language="eng">Parameter free Non-intrusive Load Monitoring (NILM) algorithms are a major step toward real-world NILM scenarios. The identification of appliances is the key element in NILM. The task consists of identification of the appliance category and its current state. In this paper, we present a param- eter free appliance identification algorithm for NILM using a 2D representation of time series known as unthresholded Recurrence Plots (RP) for appliance category identification. One cycle of voltage and current (V-I trajectory) are transformed into a RP and classified using a Spacial Pyramid Pooling Convolutional Neural Network architecture. The performance of our approach is evaluated on the three public datasets COOLL, PLAID and WHITEDv1.1 and compared to previous publications. We show that compared to other approaches using our architecture no initial parameters have to be manually tuned for each specific dataset.</abstract>
    <parentTitle language="eng">2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)</parentTitle>
    <identifier type="url">https://doi.org/10.1109/ICMLA52953.2021.00025</identifier>
    <enrichment key="PeerReviewed">Ja</enrichment>
    <enrichment key="RS_Correlation">Ja</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <author>Marc Wenninger</author>
    <author>Sebastian P. Bayerl</author>
    <author>Andreas Maier</author>
    <author>Jochen Schmidt</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>NILM</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>V-I trajectory</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Recurrence Plot</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>1718</id>
    <completedYear>2021</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>15</pageNumber>
    <edition/>
    <issue>176</issue>
    <volume>8</volume>
    <type>article</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">DEDDIAG, a domestic electricity demand dataset of individual appliances in Germany</title>
    <abstract language="eng">Real-world domestic electricity demand datasets are the key enabler for developing and evaluating machine learning algorithms that facilitate the analysis of demand attribution and usage behavior. Breaking down the electricity demand of domestic households is seen as the key technology for intelligent smart-grid management systems that seek an equilibrium of electricity supply and demand. For the purpose of comparable research, we publish DEDDIAG, a domestic electricity demand dataset of individual appliances in Germany. The dataset contains recordings of 15 homes over a period of up to 3.5 years, wherein total 50 appliances have been recorded at a frequency of 1 Hz. Recorded appliances are of significance for load-shifting purposes such as dishwashers, washing machines and refrigerators. One home also includes three-phase mains readings that can be used for disaggregation tasks. Additionally, DEDDIAG contains manual ground truth event annotations for 14 appliances, that provide precise start and stop timestamps. Such annotations have not been published for any long-term electricity dataset we are aware of.</abstract>
    <parentTitle language="eng">Scientific Data</parentTitle>
    <identifier type="url">https://doi.org/10.1038/s41597-021-00963-2</identifier>
    <enrichment key="PeerReviewed">Ja</enrichment>
    <enrichment key="RS_Acronym">LV-selbstlernend</enrichment>
    <enrichment key="RS_Correlation">Ja</enrichment>
    <enrichment key="RS_ProjectTitle">Erhöhung des Lastverschiebungspotenzials durch selbstlernende Home Automation Algorithmen mit flexiblen Optimierungskriterien</enrichment>
    <enrichment key="RS_FundingAgency">BMBF</enrichment>
    <enrichment key="RS_GrantNumber">01LY1506</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <author>Marc Wenninger</author>
    <author>Andreas Maier</author>
    <author>Jochen Schmidt</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Machine Learning</value>
    </subject>
    <collection role="ddc" number="05">Zeitschriften, fortlaufende Sammelwerke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>292</id>
    <completedYear>2007</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>294</pageFirst>
    <pageLast>301</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>Springer-Verlag</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Automatic Evaluation of Pathologic Speech - from Research to Routine Clinical Use</title>
    <abstract language="eng">Previously we have shown that ASR technology can be used to objectively evaluate pathologic speech. Here we report on progress for routine clinical use: 1) We introduce an easy-to-use recording and evaluation environment. 2) We confirm our previous results for a larger group of patients. 3) We show that telephone speech can be analyzed with the same methods with only a small loss of agreement with human experts. 4) We show that prosodic information leads to more robust results. 5) We show that text reference instead of transliteration can be used for evaluation. Using word accuracy of a speech recognizer and prosodic features as features for SVM regression, we achieve a correlation of .90 between the automatic analysis and human experts.</abstract>
    <parentTitle language="eng">TSD 2007, 10th International Conference on Text, Speech and Dialogue, Pilsen, Czech Republic, September 2007.</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Elmar Nöth</author>
    <author>Andreas Maier</author>
    <author>Tino Haderlein</author>
    <author>Korbinian Riedhammer</author>
    <author>Frank Rosanowski</author>
    <author>Maria Schuster</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Automatic Speech Recognition</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Pathologic Speech</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Automatic Evaluation</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Prosodic Feature</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech Recognizer</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>291</id>
    <completedYear>2007</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>238</pageFirst>
    <pageLast>245</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>Springer-Verlag</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">An Automatic Version of the Post-Laryngectomy Telephone Test</title>
    <abstract language="eng">Tracheoesophageal (TE) speech is a possibility to restore the ability to speak after total laryngectomy, i.e. the removal of the larynx. The quality of the substitute voice has to be evaluated during therapy. For the intelligibility evaluation of German speakers over telephone, the Post-Laryngectomy Telephone Test (PLTT) was defined. Each patient reads out 20 of 400 different monosyllabic words and 5 out of 100 sentences. A human listener writes down the words and sentences understood and computes an overall score. This paper presents a means of objective and automatic evaluation that can replace the subjective method. The scores of 11 naïve raters for a set of 31 test speakers were compared to the word recognition rate of speech recognizers. Correlation values of about 0.9 were reached.</abstract>
    <parentTitle language="eng">TSD 2007, 10th International Conference on Text, Speech and Dialogue, Proceedings, Pilsen, Czech Republic, September 2007.</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Tino Haderlein</author>
    <author>Korbinian Riedhammer</author>
    <author>Andreas Maier</author>
    <author>Elmar Nöth</author>
    <author>Hikmet Toy</author>
    <author>Frank Rosanowski</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Automatic Speech Recognition</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Mono Poly</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Total Laryngectomy</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech Recognition System</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Automatic Evaluation</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>290</id>
    <completedYear>2007</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>717</pageFirst>
    <pageLast>722</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Towards Robust Automatic Evaluation of Pathologic Telephone Speech</title>
    <abstract language="eng">For many aspects of speech therapy an objective evaluation of the intelligibility of a patient's speech is needed. We investigate the evaluation of the intelligibility of speech by means of automatic speech recognition. Previous studies have shown that measures like word accuracy are consistent with human experts' ratings. To ease the patient's burden, it is highly desirable to conduct the assessment via phone. However, the telephone channel influences the quality of the speech signal which negatively affects the results. To reduce inaccuracies, we propose a combination of two speech recognizers. Experiments on two sets of pathological speech show that the combination results in consistent improvements in the correlation between the automatic evaluation and the ratings by human experts. Furthermore, the approach leads to reductions of 10% and 25% of the maximum error of the intelligibility measure.</abstract>
    <parentTitle language="eng">2007 IEEE Workshop on Automatic Speech Recognition &amp; Understanding (ASRU), Kyoto, Japan, December 2007.</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Korbinian Riedhammer</author>
    <author>Georg Stemmer</author>
    <author>Tino Haderlein</author>
    <author>Mario Schuster</author>
    <author>Frank Rosanowski</author>
    <author>Elmar Nöth</author>
    <author>Andreas Maier</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Biomedical acoustics</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech intelligibility</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech processing</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Acoustic applications</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>281</id>
    <completedYear>2009</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>2015</pageFirst>
    <pageLast>2018</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation>ACM New York, NY, USA ©2009</creatingCorporation>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Towards a Language-independent Intelligibility Assessment of Children with Cleft Lip and Palate</title>
    <abstract language="eng">We describe a novel evaluation system for the intelligibility assessment of children with CLP on standardized tests. The system is solely based on standard cepstral features in form of MFCCs. No other information like word alignments is used. So the system can be easily adapted to other languages. For each child one GMM is created by adaptation of a UBM to the speaker-specific MFCCs. The components of this GMM are concatenated in order to create a so-called GMM supervector. These GMM supervectors are then used as meta features for an SVR. We evaluated our language-independent system on two different datasets of children suffering from CLP. One dataset contains recordings of 35 German children, where the children named different pictograms. The other dataset contains recordings of 14 Italian speaking children, who repeated standardized sentences. On both datasets we achieved high correlations: up to 0.81 for the German dataset and 0.83 for the Italian dataset.</abstract>
    <parentTitle language="eng">WOCCI '09 Proceedings of the 2nd Workshop on Child, Computer and Interaction (WOCCI 2009), Cambridge, Massachusetts, November 2009, Article No. 6.</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Tobias Bocklet</author>
    <author>Andreas Maier</author>
    <author>Korbinian Riedhammer</author>
    <author>Elmar Nöth</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech Recognition</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
  <doc>
    <id>263</id>
    <completedYear>2014</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Erlangen-CLP: A Large Annotated Corpus of Speech from Children with Cleft Lip and Palate.</title>
    <abstract language="deu">In this paper we describe Erlangen-CLP, a large speech database of children with Cleft Lip and Palate. More than 800 German children with CLP (most of them between 4 and 18 years old) and 380 age matched control speakers spoke the semi-standardized PLAKSS test that consists of words with all German phonemes in different positions. So far 250 CLP speakers were manually transcribed, 120 of these were analyzed by a speech therapist and 27 of them by four additional therapists.  The tharapists marked 6 different processes/criteria like pharyngeal backing and hypernasality which typically occur in speech of people with CLP. We present detailed statistics about the the marked processes and the inter-rater agreement.</abstract>
    <parentTitle language="eng">Language Resources and Evaluation Conference (LREC), Reykjavik, Iceland, May 2014.</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Tobias Bocklet</author>
    <author>Andreas Maier</author>
    <author>Korbinian Riedhammer</author>
    <author>Ulrich Eysholdt</author>
    <author>Elmar Nöth</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Cleft Lip and palate</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>pathologic speech</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Children's Speech</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
  </doc>
  <doc>
    <id>310</id>
    <completedYear>2009</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>deu</language>
    <pageFirst>51</pageFirst>
    <pageLast>56</pageLast>
    <pageNumber/>
    <edition/>
    <issue>57</issue>
    <volume>2009</volume>
    <type>contributiontoperiodical</type>
    <publisherName>Springer-Verlag</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-06-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="deu">Automatisierung des Postlaryngektomie-Telefontests</title>
    <abstract language="deu">In dieser Studie wird ein objektives Verfahren für die Verständlichkeitsmessung mit dem Postlaryngektomie-Telefontest (PLTT) mittels automatischer Spracherkennungstechnik beschrieben.&#13;
31 Sprecher mit tracheoösophagealer Ersatzstimme (25 Männer und 6 Frauen; 63,4±8,7 Jahre) wurden zunächst von 11 naiven Hörern bewertet. Der vom Spracherkennungssystem ermittelte Verständlichkeitsgrad wird als Prozentsatz korrekt verstandener Wörter einer Wortkette, der Wortakkuratheit bzw. -korrektheit, angegeben und mit den subjektiv ermittelten PLTT-Werten verglichen.&#13;
Die durchschnittliche PLTT-Gesamtverständlichkeit der 11 naiven Hörer liegt bei 47%, die automatisch ermittelte Wortakkuratheit und Wortkorrektheit liegen deutlich niedriger (etwa 0% bzw. etwa 15%). Die Korrelation zwischen menschlicher und maschineller Bewertung liegt jedoch z. T. über 0,9.&#13;
Für den Gesamtverständlichkeitswert des PLTT kann mit Hilfe der automatischen Spracherkennung objektiv und effizient ein äquivalentes Maß berechnet werden.</abstract>
    <parentTitle language="deu">HNO</parentTitle>
    <enrichment key="review.accepted_by">2</enrichment>
    <author>Tino Haderlein</author>
    <author>Korbinian Riedhammer</author>
    <author>Andreas Maier</author>
    <author>Elmar Nöth</author>
    <author>Ulrich Eysholdt</author>
    <author>Frank Rosanowski</author>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Spracherkennungssoftware</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Automatische Mustererkennung</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Sprechverständlichkeit</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Auswertungsmethoden</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Korrelation von Daten</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <thesisPublisher>Technische Hochschule Rosenheim</thesisPublisher>
  </doc>
</export-example>
