LZI - Schloss Dagstuhl - Talks + Materials of Seminar 13451
 Functions: 

Seminar 13451
Computational Audio Analysis

Meinard Müller (Universität Erlangen-Nürnberg, DE), Shrikanth S. Narayanan (USC - Los Angeles, US), Björn Schuller (TU München, DE)

Caveat: Due to caching problems of dynamic webpages, sometimes newly
uploaded files are not shown. Please reload the page accordingly.

 

Seminar Wide Materials
 
 Interaction and Affect
Abstracts: txt Slides: pptx

 Small Data
Slides: pptx

 Unsupervised learning for audio
Abstracts: txt Slides: pptx

 Learning of Units and Knowledge Representation
Slides: pptx

 Unsupervised Learning for Audio: A Case Study on Car Crash Detection
Slides: pptx

 Blind Source Separation
Abstracts: txt Slides: pdf

 


Xavier Anguera , Telefónica Research - Barcelona
 Multimedia analysis for the poor (in training resources)
Abstracts: txt

 

Jon Barker , University of Sheffield
 Engineering selective attention into acoustic scene analysis systems
Abstracts: txt

 

Stephan Baumann , DFKI - Kaiserslautern
 Social Multimedia: Sentiment / Recommendation / Prediction / Big Data / LOD
Abstracts: txt

 

Murtaza Bulut , Philips Research Lab. - Eindhoven
 Audio processing for people's benefit
Abstracts: txt

 Audio processing for health and wellbeing
Abstracts: txt Slides: pptx

 

Carlos Busso , The University of Texas at Dallas
 Compensate lexical/speaker/environment variability for speech emotion recognition
Abstracts: txt Slides: pdf

 

Nick Campbell , Trinity College Dublin
 Social Prosody - speech technology & human conversational interaction
Abstracts: txt Paper: pdf

 

Laurence Devillers , LIMSI - Orsay
 Affective and social dimension detection in spoken dialogues
Abstracts: txt Other: pdf

 

Jonathan Driedger , Universität Erlangen-Nürnberg
 Perceptually appealing reconstruction of spectrally modified signals
Abstracts: txt

 

Bernd Edler , Universität Erlangen-Nürnberg
 Time-Frequency Decompositions
Abstracts: txt

 

Anna Esposito , Intern. Institute for Advanced Scientific Studies
 Emotional expressions: Communicative displays or psychological universals?
Abstracts: txt

 

Sebastian Ewert , Queen Mary University of London
 Integration of prior knowledge
Abstracts: txt

 

Cedric Fevotte , JL Lagrange Laboratory- Nice
 NMF meet dynamics
Abstracts: txt

 

Jort Gemmeke , KU Leuven
 Zero resource speech interfaces
Abstracts: txt Slides: pdf

 Noise robust speech recognition
Abstracts: txt

 

Franz Graf , Joanneum Research - Graz
 Computational Audio Analysis beyond laboratory conditions
Abstracts: txt

 

Martin Heckmann , Honda Research Europe - Offenbach
 Is it all machine learning?
Abstracts: txt

 

Dorothea Kolossa , Ruhr-Universität Bochum
 Discriminative audio features for noisy environments
Abstracts: txt Slides: pptx

 

Gernot Kubin , TU Graz
 Speech Communication: From L2 Norms to L2 Learning
Abstracts: txt

 

Frank Kurth , Fraunhofer FKIE - Wachtberg
 Detection of Repeated Signal Components and Applications to Audio Analysis
Abstracts: txt

 

Sungbok Lee , University of Southern California
 Prosody representation and interactive speech prosody processing
Abstracts: txt

 

Florian Metze , Carnegie Mellon University
 Audio and Multimedia Methods for Large-Scale Video Analysis
Abstracts: txt Paper: pdf

 

Roger K. Moore , University of Sheffield
 Interpreting 'intentional' behaviour
Abstracts: txt Slides: pdf

 

Emily Mower Provost , University of Michigan - Ann Arbor
 Emotion Modeling for Mental Health
Abstracts: txt

 

Meinard Mueller , Universität Erlangen-Nürnberg
 Informed source separation for music signals
Abstracts: txt

 

Shrikanth S. Narayanan , University of Southern California
 Human production and processing of sounds
Abstracts: txt

 

Nobutaka Ono , National Institute of Informatics - Tokyo
 Adhoc Microhone Array for Source Seaparation and Localization
Abstracts: txt

 

Bryan Pardo , Northwestern University - Evanston
 Learning sounds from mixtures with a small number of examples
Abstracts: txt

 

Alexandros Potamianos , National TU Athens
 Semantic-Affective Models for Multimodal Signal Processing
Abstracts: txt

 

Bhiksha Raj , Carnegie Mellon University
 Automatic Structure Discovery in "Wild" Audio
Abstracts: txt

 

Gaël Richard , Telecom ParisTech
 Exploitation of human perception principles in audio processing systems
Abstracts: txtpdf Slides: pdf

 Informed source separation
Abstracts: txt

 Sparse representations for audio processing
Abstracts: txt

 

Mark Sandler , Queen Mary University of London
 Content Analysis at Source for improved semantic representation
Abstracts: txt

 

Bjoern Schuller , TU München
 Approaching Cross-Audio Computer Audition
Abstracts: txt

 

Joan Serrà , IIIA - CSIC - Barcelona
 What can we learn from massive music archives?
Abstracts: txtpdf

 

Rita Singh , Carnegie Mellon University
 An alternate perspective to classification over large hypothesis spaces
Abstracts: txt

 

Paris Smaragdis , University of Illinois - Urbana
 Stop listening to speech, language and vision people!
Abstracts: txt

 

Stefano Squartini , Polytechnic University of Marche
 Acoustic Monitoring in Smart Home Environments: an holistic perspective
Abstracts: txt Slides: pdf

 

Shiva Sundaram , Audyssey Laboratories
 Data-driven Latent Audio Representations
Abstracts: txt

 

Khiet Truong , University of Twente
 Beyond words - extracting and interpreting paralinguistic information in conversation
Abstracts: txt

 

Christian Uhle , Fraunhofer IIS - Erlangen
 Decomposition of audio signals into 2 complementary signals
Abstracts: txt

 

Emmanuel Vincent , INRIA - Nancy - Grand Est
 Sound processing in everyday environments
Abstracts: txt

 

Tuomas Virtanen , Tampere University of Technology
 Sound event detection and recognition in everyday environments
Abstracts: txt Slides: pdf

 Signal processing for audio content analysis
Abstracts: txt

 



License

Creative Commons License
This webpage and the material that is made available on this webpage is licensed under a
Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 Unported License.

The CC by-nc-nd license allows you to copy, distribute and transmit the work under the following conditions: