TH1.P1.14
EVALUATION OF OBJECTIVE QUALITY MODELS ON NEURAL AUDIO CODECS
Thomas Muller, Stéphane Ragot, Vincent Barriac, Orange Innovation, France; Pascal Scalart, IRISA - University of Rennes, France
Session:
TH1.P1: Poster Session VI: Acoustic echo and feedback suppression, Active noise control, Speech intelligibility enhancement, Quality and intelligibility assessment Poster
Track:
Acoustic echo and feedback suppression
Location:
Nedre Foyer
Presentation Time:
Thu, 12 Sep, 10:00 - 12:00 Central European Time (UTC +1)
Session Chair:
Ann Spriet, Goodix Technology (Belgium) B.V.
Presentation
Discussion
Resources
No resources available.
Session TH1.P1
TH1.P1.1: ONLINE SYSTEM IDENTIFICATION ON LEARNED ACOUSTIC MANIFOLDS USING AN EXTENDED KALMAN FILTER
Till Hardenbicker, Peter Jax, RWTH Aachen University, Germany
TH1.P1.2: A HYBRID APPROACH FOR LOW-COMPLEXITY JOINT ACOUSTIC ECHO AND NOISE REDUCTION
Shrishti Saha Shetu, Naveen Kumar Desiraju, Jose Miguel Martinez Aponte, Emanuel A. P. Habets, Edwin Mabande, Fraunhofer-Institut für Integrierte Schaltungen (IIS), Germany
TH1.P1.4: A CASCADED SEMI-BLIND SOURCE SEPARATION METHOD FOR JOINT ACOUSTIC ECHO CANCELLATION, INTERFERENCE SUPPRESSION, AND NOISE REDUCTION
Xianrui Wang, Northwestern Polytechnical University, China; Kaien Mo, Waseda University, Japan; Yichen Yang, Northwestern Polytechnical University, China; Liyuan Zhang, Shoji Makino, Waseda University, Japan; Jingdong Chen, Northwestern Polytechnical University, China
TH1.P1.5: A DATA-REUSE SEMI-BLIND SOURCE SEPARATION APPROACH FOR NONLINEAR ACOUSTIC ECHO CANCELLATION
Yichen Yang, Xianrui Wang, Northwestern Polytechnical University, China; Andreas Brendel, Fraunhofer Institute for Integrated Circuits (IIS), Germany; Wen Zhang, Northwestern Polytechnical University, China; Jacob Benesty, University of Quebec, Canada; Shoji Makino, Waseda University, Japan; Jingdong Chen, Northwestern Polytechnical University, China
TH1.P1.6: SAMPLE RATE OFFSET COMPENSATED ACOUSTIC ECHO CANCELLATION FOR MULTI-DEVICE SCENARIOS
Srikanth Korse, Oliver Thiergart, Emanuël Habets, International Audio Laboratories Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany
TH1.P1.7: LOW-ORDER CONTROLLERS FOR ACTIVE NOISE CANCELLATION BASED ON HANKEL MATRIX RANK MINIMIZATION
Florian Hilgemann, Peter Jax, RWTH Aachen University, Germany
TH1.P1.8: A MULTI-NOISE MULTI-CHANNEL ANC SYSTEM USING RELATIVE TRANSFER MATRIX-BASED APPROACH
Yile (Angela) Zhang, Thushara Abhayapala, The Australian National University, Australia; Huiyuan Sun, The University of Sydney, Australia; Prasanga Samarasinghe, Amy Bastine, The Australian National University, Australia
TH1.P1.9: ACTIVE ROAD NOISE CONTROL BASED ON DATA-DRIVEN PREDICTIONS OF PASSENGER EAR NOISE SIGNAL
Zining Liang, Hucheng Wang, Yichen Yang, Wen Zhang, Northwestern Polytechnical University, China; Thushara Abhayapala, The Australian National University, Australia
TH1.P1.10: PREDICTING SUBJECTIVE SATISFACTION WITH SPEECH PREDICTION-BASED ANC USING PERCEPTUALLY RELEVANT METRICS CORRELATED WITH SOUND ATTRIBUTES
Yurii Iotov, Audio Analysis Lab, Dept. of Electronic Systems, Aalborg University, Denmark, Denmark; Rasmus Elofsson, Sidsel Marie Nørholm, GN Audio A/S, Ballerup, Denmark, Denmark; Mads Græsbøll Christensen, Audio Analysis Lab, Dept. of Electronic Systems, Aalborg University, Denmark, Denmark
TH1.P1.11: NEAR-END LISTENING ENHANCEMENT USING A NOISE-ROBUST LINEAR TIME-INVARIANT FILTER
Filippo Villani, Aalborg University, Denmark; Wai-Yip Chan, Queen’s University, Canada; Zheng-Hua Tan, Jan Østergaard, Aalborg University, Denmark; Jesper Jensen, Aalborg University and Oticon A/S, Denmark
TH1.P1.12: MAGNITUDE OR PHASE? A TWO-STAGE ALGORITHM FOR SINGLE-MICROPHONE SPEECH DEREVERBERATION
Ayal Schwartz, OriginAI, Israel; Sharon Gannot, Bar-Ilan University, Israel; Shlomo E. Chazan, OriginAI, Bar-Ilan University, Israel
TH1.P1.13: CONVOLUTIONAL NEURAL NETWORK-BASED PREDICTION OF A FRENCH MODIFIED RHYME TEST RECORDED WITH A BODY-CONDUCTION MICROPHONE
Thomas Joubaud, Véronique Zimpfer, French-German Research Institute of Saint-Louis, France
TH1.P1.14: EVALUATION OF OBJECTIVE QUALITY MODELS ON NEURAL AUDIO CODECS
Thomas Muller, Stéphane Ragot, Vincent Barriac, Orange Innovation, France; Pascal Scalart, IRISA - University of Rennes, France
TH1.P1.15: EVALUATING SPEECH ENHANCEMENT SYSTEMS THROUGH LISTENING EFFORT
Femke B. Gelderblom, Tron V. Tronstad, SINTEF Digital, Norway; Iván López-Espejo, University of Granada, Spain