@inproceedings{SpieglRiedhammerSteidletal.2010, author = {Spiegl, Werner and Riedhammer, Korbinian and Steidl, Stefan and N{\"o}th, Elmar}, title = {FAU IISAH Corpus - A German Speech Database Consisting of Human-Machine and Human-Human Interaction Acquired by Close-Talking and Far-Distance Microphones}, series = {7th Conference on International Language Resources and Evaluation (LREC 2010), European Language Resources Association (ELRA), Valletta, Malta, May 2010.}, booktitle = {7th Conference on International Language Resources and Evaluation (LREC 2010), European Language Resources Association (ELRA), Valletta, Malta, May 2010.}, pages = {2420 -- 2423}, year = {2010}, language = {en} } @inproceedings{BockletMaierRiedhammeretal.2009, author = {Bocklet, Tobias and Maier, Andreas and Riedhammer, Korbinian and N{\"o}th, Elmar}, title = {Towards a Language-independent Intelligibility Assessment of Children with Cleft Lip and Palate}, series = {WOCCI '09 Proceedings of the 2nd Workshop on Child, Computer and Interaction (WOCCI 2009), Cambridge, Massachusetts, November 2009, Article No. 6.}, booktitle = {WOCCI '09 Proceedings of the 2nd Workshop on Child, Computer and Interaction (WOCCI 2009), Cambridge, Massachusetts, November 2009, Article No. 6.}, organization = {ACM New York, NY, USA ©2009}, pages = {2015 -- 2018}, year = {2009}, abstract = {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.}, language = {en} } @inproceedings{FariaRiedhammerJaninetal.2016, author = {Faria, Arlo and Riedhammer, Korbinian and Janin, Adam and Bauer, A.}, title = {REMEETING: Searchable Conversations}, series = {INTERSPEECH 2016, Annual Conference of the International Speech Communication Association (ISCA), IEEE Workshop on Spoken Language Technologies (SLT), San Francisco, USA, September 2016.}, booktitle = {INTERSPEECH 2016, Annual Conference of the International Speech Communication Association (ISCA), IEEE Workshop on Spoken Language Technologies (SLT), San Francisco, USA, September 2016.}, organization = {2016 ISCA}, year = {2016}, language = {en} } @inproceedings{FariaRiedhammer2015, author = {Faria, Arlo and Riedhammer, Korbinian}, title = {REMEETING — Get More Out Of Meetings}, series = {INTERSPEECH 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 2015.}, booktitle = {INTERSPEECH 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 2015.}, year = {2015}, abstract = {Remeeting is a tool that helps you get more out of in-person meetings. Calendar integration and a special email address allow users to email agenda items prior to a certain meeting. A discrete notification at the time of the meeting reminds the user to start the recording. During the meeting, the user focuses on the conversation, or can add notes and photos if desired. After the meeting, every participant gets notified by an automated email that lists the participants along with automatically extracted keywords, notes and photos. This stimulates collaboration, and keeps follow-up contributions at a central place: Just reply to add further notes to the meeting. The resulting meeting "document" can be shared with others and reviewed using a web app that acts as a visual index to the meeting. This makes Remeeting the perfect tool for regular group meetings, standups and interviews, where people typically track progress and follow up on. Remeeting is leveraging, promoting and contributing to open source projects including kaldi and docker.}, language = {en} } @inproceedings{FariaRiedhammer2014, author = {Faria, Arlo and Riedhammer, Korbinian}, title = {REMEETING — Get More Out of Meetings}, series = {INTERSPEECH 2014, 15th Annual Conference of the International Speech Communication Association, IEEE Workshop on Spoken Language Technologies (SLT), Singapore, September 2014.}, booktitle = {INTERSPEECH 2014, 15th Annual Conference of the International Speech Communication Association, IEEE Workshop on Spoken Language Technologies (SLT), Singapore, September 2014.}, year = {2014}, language = {en} } @inproceedings{GargFavreRiedhammeretal.2009, author = {Garg, Nikhil and Favre, Benoit and Riedhammer, Korbinian and Hakkani-T{\"u}r, Dilek}, title = {A Graph Based Method for Meeting Summarization}, series = {INTERSPEECH 2009, 10th Annual Conference of the International Speech Communication Association, Brighton, United Kingdom, September 2009.}, booktitle = {INTERSPEECH 2009, 10th Annual Conference of the International Speech Communication Association, Brighton, United Kingdom, September 2009.}, pages = {1499 -- 1502}, year = {2009}, abstract = {This paper presents an unsupervised, graph based approach for extractive summarization of meetings. Graph based methods such as TextRank have been used for sentence extraction from news articles. These methods model text as a graph with sentences as nodes and edges based on word overlap. A sentence node is then ranked according to its similarity with other nodes. The spontaneous speech in meetings leads to incomplete, informed sentences with high redundancy and calls for additional measures to extract relevant sentences. We propose an extension of the TextRank algorithm that clusters the meeting utterances and uses these clusters to construct the graph. We evaluate this method on the AM I meeting corpus and show a significant improvement over TextRank and other baseline methods.}, language = {en} } @inproceedings{GillickRiedhammerFavreetal.2009, author = {Gillick, Dan and Riedhammer, Korbinian and Favre, Benoit and Hakkani-T{\"u}r, Dilek}, title = {A Global Optimization Framework for Meeting Summarization}, series = {2009 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Taipei, Taiwan, April 2009.}, booktitle = {2009 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Taipei, Taiwan, April 2009.}, pages = {4769 -- 4772}, year = {2009}, abstract = {We introduce a model for extractive meeting summarization based on the hypothesis that utterances convey bits of information, or concepts. Using keyphrases as concepts weighted by frequency, and an integer linear program to determine the best set of utterances, that is, covering as many concepts as possible while satisfying a length constraint, we achieve ROUGE scores at least as good as a ROUGE-based oracle derived from human summaries. This brings us to a critical discussion of ROUGE and the future of extractive meeting summarization.}, language = {en} } @inproceedings{RiedhammerFavreHakkaniTuer2008, author = {Riedhammer, Korbinian and Favre, Benoit and Hakkani-T{\"u}r, Dilek}, title = {A Keyphrase Based Approach to Interactive Meeting Summarization}, series = {2008 IEEE Workshop on Spoken Language Technologies (SLT), Goa, India, December 2008.}, booktitle = {2008 IEEE Workshop on Spoken Language Technologies (SLT), Goa, India, December 2008.}, pages = {153 -- 156}, year = {2008}, abstract = {Rooted in multi-document summarization, maximum marginal relevance (MMR) is a widely used algorithm for meeting summarization (MS). A major problem in extractive MS using MMR is finding a proper query: the centroid based query which is commonly used in the absence of a manually specified query, can not significantly outperform a simple baseline system. We introduce a simple yet robust algorithm to automatically extract keyphrases (KP) from a meeting which can then be used as a query in the MMR algorithm. We show that the KP based system significantly outperforms both baseline and centroid based systems. As human refined KPs show even better summarization performance, we outline how to integrate the KP approach into a graphical user interface allowing interactive summarization to match the user's needs in terms of summary length and topic focus.}, language = {en} } @inproceedings{TurStolckeVossetal.2008, author = {Tur, Gokhan and Stolcke, Andreas and Voss, Lynn and Dowding, John and Favre, Benoit and Fernandez, Raquel and Frampton, Matthew and Frandsen, Michael and Frederickson, Clive and Graciarena, Martin and Hakkani-T{\"u}r, Dilek and Kintzing, Donald and Leveque, Kyle and Mason, Shane and Niekrasz, John and Peters, Stanley and Purver, Matthew and Riedhammer, Korbinian and Shriberg, Elizabeth and Tien, Jing and Vergyri, Dimitra and Yang, Fan}, title = {The CALO Meeting Speech Recognition and Understanding System}, series = {2008 IEEE Workshop on Spoken Language Technologies (SLT), Goa, India, December 2008.}, booktitle = {2008 IEEE Workshop on Spoken Language Technologies (SLT), Goa, India, December 2008.}, pages = {69 -- 72}, year = {2008}, abstract = {The CALO meeting assistant provides for distributed meeting capture, annotation, automatic transcription and semantic analysis of multiparty meetings, and is part of the larger CALO personal assistant system. This paper summarizes the CALO-MA architecture and its speech recognition and understanding components, which include real-time and offline speech transcription, dialog act segmentation and tagging, question-answer pair identification, action item recognition, decision extraction, and summarization.}, language = {en} } @inproceedings{RiedhammerGillickFavreetal.2008, author = {Riedhammer, Korbinian and Gillick, Dan and Favre, Benoit and Hakkani-T{\"u}r, Dilek}, title = {Packing the Meeting Summarization Knapsack}, series = {INTERSPEECH 2008, 9th Annual Conference of the International Speech Communication Association (ISCA), Brisbane, Australia, September 2008.}, booktitle = {INTERSPEECH 2008, 9th Annual Conference of the International Speech Communication Association (ISCA), Brisbane, Australia, September 2008.}, pages = {2434 -- 2437}, year = {2008}, abstract = {Despite considerable work in automatic meeting summarization over the last few years, comparing results remains difficult due to varied task conditions and evaluations. To address this issue, we present a method for determining the best possible extractive summary given an evaluation metric like ROUGE. Our oracle system is based on a knapsack-packing framework, and though NP-Hard, can be solved nearly optimally by a genetic algorithm. To frame new research results in a meaningful context, we suggest presenting our oracle results alongside two simple baselines. We show oracle and baseline results for a variety of evaluation scenarios that have recently appeared in this field.}, language = {en} } @inproceedings{RiedhammerStemmerHaderleinetal.2007, author = {Riedhammer, Korbinian and Stemmer, Georg and Haderlein, Tino and Schuster, Mario and Rosanowski, Frank and N{\"o}th, Elmar and Maier, Andreas}, title = {Towards Robust Automatic Evaluation of Pathologic Telephone Speech}, series = {2007 IEEE Workshop on Automatic Speech Recognition \& Understanding (ASRU), Kyoto, Japan, December 2007.}, booktitle = {2007 IEEE Workshop on Automatic Speech Recognition \& Understanding (ASRU), Kyoto, Japan, December 2007.}, pages = {717 -- 722}, year = {2007}, abstract = {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.}, language = {en} }