Elmar Nöth

Automatic Speech Recognition Systems for the Evaluation of Voice and Speech Disorders in Head and Neck Cancer (2010)

Andreas Maier, Tino Haderlein, Florian Stelzle, Elmar Nöth, Emeka Nkenke, Frank Rosanowski, ...

In patients suffering from head and neck cancer, speech intelligibility is often restricted. For assessment and outcome measurements, automatic speech recognition systems have previously been shown...

Laryngealizations and Emotions: How Many Babushkas? (2009)

Anton Batliner, Stefan Steidl, Elmar Nöth

It has been claimed that voice quality traits including irregular phonation such as creaky voice (laryngealization) serve several functions, amongst them being the marking of emotions; accordingly,...

Aspects of Named Entity Processing (2008)

Michael Levit, Patrick Haffner, Allen Gorin, Hiyan Alshawi, Elmar Nöth

In this paper we investigate the utility of three aspects of named entity processing: detection, localization and value extraction. We corroborate this task categorization by providing examples of...

To Talk or not to Talk with a Computer: On-Talk vs. Off-Talk. (2008)

Anton Batliner, Christian Hacker, Elmar Nöth

Abstract. If no specific precautions are taken, people talking to a computer can – the same way as while talking to another human – speak aside, either to themselves or to another person. On the...

A Taxonomy of Applications that Utilize Emotional Awareness (2008)

Anton Batliner, Felix Burkhardt, Markus Van Ballegooy, Elmar Nöth

This paper deals with human-computer interaction applications that utilize emotional awareness. We will confine our discussion on speech-based applications. Prerequisites — training data,...

Visualization of Voice Disorders Using the Sammon Transform (2008)

Tino Haderlein, Dominik Zorn, Stefan Steidl, Elmar Nöth, Maria Schuster

Abstract. The Sammon Transform performs data projections in a topology-preserving manner on the basis of an arbitrary distance measure. We use the weights of the observation probabilities of...

MAXIMUM LIKELIHOOD ESTIMATION OF A REVERBERATION MODEL FOR ROBUST DISTANT-TALKING SPEECH RECOGNITION (2008)

Armin Sehr, Yuanhang Zheng, Elmar Nöth, Walter Kellermann

We propose a novel approach for estimating a reverberation model for a robust recognizer according to [1], which is designed to allow distant-talking automatic speech recognition (ASR) in reverberant...

Aspects of Named Entity Processing (2008)

Michael Levit, Patrick Haffner, Allen Gorin, Hiyan Alshawi, Elmar Nöth

In this paper we investigate the utility of three aspects of named entity processing: detection, localization and value extraction. We corroborate this task categorization by providing examples of...

Boiling down Prosody for the Classification of Boundaries and Accents in (2008)

German And English, Anton Batliner, Jan Buckow, Richard Huber, Volker Warnke, Elmar Nöth, ...

In the focus of this paper is a comparison of the most relevant prosodic features/feature classes for the classification of boundaries and accents in German and in English. Principal components were...

Prosodic Models, Automatic Speech Understanding, and Speech Synthesis: (2008)

Towards The Common, Anton Batliner, Bernd Möbius, Gregor Möhler, Antje Schweitzer, Elmar Nöth

Automatic speech understanding and speech synthesis, two of the major speech processing applications, impose strikingly different constraints and requirements on prosodic models. The prevalent models...

Using Speech and Gesture to . . . (2008)

Rui P. Shi, Johann Adelhardt, Rui P. Shi, Johann Adelhardt, Dokument Teilprojekt, ...

Modern dialogue systems should interpret the users' behavior and mind in the same way as human beings do. That means in a multimodal manner, where communication is not limited to verbal...

Recognition of Selected Prosodic Events in Slovenian Speech (2007)

France Mihelič, Jerneja Gros, Elmar Nöth

Prosodic annotation procedures of the GOPOLIS Slovenian speech data database and methods for automatic classification of different prosodic events are described in the paper. Several statistical...

Caller: Computer Assisted Language Learning from Erlangen - Pronunciation Training and More (2007)

Hacker, Christian, Maier, Andreas, Hessler, Andre, Guthunz, Ute, Nöth, Elmar

In school, oral examination and the ability to speak a foreign language properly have become more important. Yet, individual time per pupil to train the correct pronunciation is extremely short....

Caller: Computer Assisted Language Learning from Erlangen - Pronunciation Training and More (2007)

Hacker, Christian, Maier, Andreas, Hessler, Andre, Guthunz, Ute, Nöth, Elmar

In school, oral examination and the ability to speak a foreign language properly have become more important. Yet, individual time per pupil to train the correct pronunciation is extremely short....

Fully Automatic Assessment of Speech of Children with Cleft Lip and Palate. Informatica 30:477–482 (2006)

Andreas Maier, Elmar Nöth, Anton Batliner, Emeka Nkenke, Maria Schuster

Cleft lip and palate (CLP) may cause functional limitations even after adequate surgical and non-surgical treatment, speech disorder being one of them. Until now, an automatic, objective means to...

Off all things the measure is man Automatic classification of emotions and inter-labeler consistency (2005)

Stefan Steidl, Michael Levit, Anton Batliner, Elmar Nöth, Heinrich Niemann

In traditional classification problems, the reference needed for training a classifier is given and considered to be absolutely correct. However, this does not apply to all tasks. In emotion...

Off all things the measure is man Automatic classification of emotions and inter-labeler consistency (2005)

Stefan Steidl, Michael Levit, Anton Batliner, Elmar Nöth, Heinrich Niemann

In traditional classification problems, the reference needed for training a classifier is given and considered to be absolutely correct. However, this does not apply to all tasks. In emotion...

Various Information Sources for HMM with Weighted Multiple Codebooks (2003)

Christian Hacker, Georg Stemmer, Stefan Steidl, Elmar Nöth, Heinrich Niemann

When semicontinuous HMM are used for acoustic modeling in speech recognition usually all states share a single codebook. In our investigations we split the feature set into independent subsets and...

A Phone Recognizer Helps to Recognize Words Better (2003)

Georg Stemmer, Viktor Zeissler, Christian Hacker, Elmar Nöth, Elmar N Oth, Heinrich Niemann

For most speech recognition systems dynamic features are the only way to incorporate temporal context into the output distributions of the HMMs. In this paper we propose an efficient method to...

Improving Children's Speech Recognition by HMM Interpolation with an Adults' Speech Recognizer (2003)

Stefan Steidl, Georg Stemmer, Christian Hacker, Elmar Nöth, Heinrich Niemann

In this paper we address the problem of building a good speech recognizer if there is only a small amount of training data available.

User States, User Strategies, and System Performance: How to Match the One with the Other (2003)

Anton Batliner, Christian Hacker, Stefan Steidl, Elmar Nöth, Jürgen Haas

Apart from the `normal' linguistic information entailed in user utterances - segmental (phone/word) information and syntactic /semantic information -- there is additional information...

Machine Vision and Applications manuscript No. (2003)

Will Be Inserted, Matthias Zobel, Joachim Denzler, Benno Heigl, Elmar Nöth, Dietrich Paulus, ...

This contribution introduces MOBSY, a fully integrated autonomous mobile service robot system. It acts as an automatic dialogue based receptionist for visitors of our institute. MOBSY incorporates...

Pass Phrase Based Speaker Recognition for Authentication (2003)

Heinz Hertlein, Dr. Robert Frischholz, Dr. Elmar Nöth, Humanscan Gmbh

Abstract: Speaker recognition in applications of our daily lives is not yet in widespread use. In order for biometric technology to make sense for real-world authentication applications and be...

Using EM-Trained String-Edit Distances for Approximate Matching of Acoustic Morphemes (2002)

Michael Levit, Elmar Nöth, Elmar N Oth, Allen Gorin

Our research concerns spoken language understanding within the domain of automated telecommunication services. In the recent papers we presented a new methodology for training of statistical language...

Nöth E.: “Using EM-trained String-Edit Distances for Approximate Matching of Acoustic Morphemes (2002)

Michael Levit, Elmar Nöth

Our research concerns spoken language understanding within the domain of automated telecommunication services. In the recent papers we presented a new methodology for training of statistical language...

Mobsy: Integration of vision and dialogue in service robots (2001)

Matthias Zobel, Matthias Zobel, Joachim Denzler, Joachim Denzler, Benno Heigl, Benno Heigl, ...

Abstract. MOBSY is a fully integrated autonomous mobile service robot system. It acts as an automatic dialogue based receptionist for visitors of our institute. MOBSY incorporates many techniques...

Acoustic Modeling of Foreign Words in a German Speech Recognition System (2001)

Georg Stemmer Elmar, Elmar Nöth, Heinrich Niemann

foreign words for a German speech recognizer. The recognition quality of foreign words is crucial for the overall performance of a system in application fields like spoken dialogue systems, when...

From: Proceedings of the ISCA Tutorial and Research Workshop on Speech recognition and understanding, Red Bank, NJ, 2001, pp. 23--28 (2001)

Whence And Whither, Anton Batliner, Elmar Nöth, Jan Buckow, Richard Huber, Volker Warnke, ...

The `case' this paper is dealing with is prosody research at the Chair for Pattern Recognition at the University of Erlangen-- Nuremberg during the last fifteen years. We want to show how this...

Duration Features in Prosodic Classification: Why Normalization Comes Second, and what they Really Encode (2001)

Anton Batliner, Elmar Nöth, Jan Buckow, Richard Huber, Volker Warnke, Heinrich Niemann

For the classification of boundaries and accents in German and English spontaneous speech in the VERBMOBIL project (speech to speech translation system), we use a large prosodic feature vector;...

Using Phrase Accent Information for Dialogue Act Recognition in Spontaneous German Speech (1999)

Matthias Nutt, Anton Batliner, Volker Warnke, Elmar Nöth, Elmar N Oth

This paper describes an approach in which phrase accent information is used for dialogue act recognition in German spontaneous speech. This application is an example of how automatically computed...

How to Label Accent Position in Spontaneous Speech Automatically With the Help of Syntactic-Prosodic Boundary Labels (1998)

N Oth, Elmar N Oth, Anton Batliner, Anton Batliner, Anton Batliner, ...

In this paper, we describe an approach that allows us to annotate accent position in German spontaneous speech with the help of syntactic--prosodic phrase boundary labels (the so-- called M labels)....

How Statistics and Prosody can guide a Chunky Parser (1998)

Manuela Boros, Jürgen Haas, Elmar Nöth, Volker Warnke, Heinrich Niemann

Introduction Following the most common architecture of spoken dialog systems as shown in Figure 1, the main task of linguistic processing is to yield a semantic representation of what the user said....

Semantic Processing Of Out-Of-Vocabulary Words In A Spoken Dialogue System (1997)

Manuela Boros, Maria Aretoulaki, Florian Gallwitz, Elmar Nöth, Heinrich Niemann

One of the most important causes of failure in spoken dialogue systems is usually neglected: the problem of words that are not covered by the system's vocabulary (out-of-vocabulary or OOV...

Nöth: Comparison of two tree-structured approaches for grapheme-to-phoneme conversion (1996)

Ove Andersen, Ariane Lazaridès, Paul Dalsgaard, Jürgen Haas, Elmar Nöth

Recently, we described a two-step self-learning approach for grapheme-to-phoneme (G2P) conversion [1]. In the first step, grapheme and phoneme strings in the training data are aligned via an...

Comparison of Two Tree-Structured Approaches for Grapheme-to-Phoneme Conversion (1996)

Ove Andersen, Roland Kuhn, Ariane Lazaridès, Paul Dalsgaard, Jürgen Haas, Elmar Nöth

Recently, we described a two-step self-learning approach for grapheme-to-phoneme (G2P) conversion [1]. In the first step, grapheme and phoneme strings in the training data are aligned via an...

Prosodic Modules for Speech Recognition and Understanding in VERBMOBIL (1996)

Wolfgang Hess, Anton Batliner, Andreas Kießling, Ralf Kompe, Elmar Nöth, Anja Petzold, ...

Within VERBMOBIL, a large project on spoken language research in Germany, two modules for detecting and recognizing prosodic events have been developed. One module operates on speech signal...