Felix Weninger

Microsoft Research (United Kingdom) — United Kingdom

Computer Science · Physical Sciences

37h-index7.2kcitations124works1.02yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech and Audio Processing(77), Music and Audio Processing(62), Speech Recognition and Synthesis(60), Emotion and Mood Recognition(21), Blind Source Separation Techniques(16)

Publications124 total

Improving Speed/Accuracy Tradeoff for Online Streaming ASR via Real-Valued and Trainable Strides
2024· 1 cited
Conformer with dual-mode chunked attention for joint online and offline ASR
Interspeech 2022·2022· 7 cited
Conformer with dual-mode chunked attention for joint online and offline ASR
arXiv (Cornell University)·2022· 1 citedOpen Access
Dual-Encoder Architecture with Encoder Selection for Joint Close-Talk and Far-Talk Speech Recognition
2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)·2021· 3 cited
ChannelAugment: Improving Generalization of Multi-Channel ASR by Training with Input Channel Randomization
2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)·2021· 2 cited
ChannelAugment: Improving generalization of multi-channel ASR by training with input channel randomization
arXiv (Cornell University)·2021Open Access
Dual-Encoder Architecture with Encoder Selection for Joint Close-Talk and Far-Talk Speech Recognition
arXiv (Cornell University)·2021Open Access
Semi-Supervised Learning with Data Augmentation for End-to-End ASR
2020· 31 cited
openXDATA: A Tool for Multi-Target Data Generation and Missing Label Completion
arXiv (Cornell University)·2020Open Access
Semi-Supervised Learning with Data Augmentation for End-to-End ASR
arXiv (Cornell University)·2020· 3 citedOpen Access
Holistic Affect Recognition Using PaNDA: Paralinguistic Non-Metric Dimensional Analysis
IEEE Transactions on Affective Computing·2019Open Access
Online Batch Normalization Adaptation for Automatic Speech Recognition
2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)·2019· 4 cited
Deep Learning Based Mandarin Accent Identification for Accent Robust ASR
2019· 40 cited
Listen, Attend, Spell and Adapt: Speaker Adapted Sequence-to-Sequence ASR
2019· 27 cited
Listen, Attend, Spell and Adapt: Speaker Adapted Sequence-to-Sequence ASR
arXiv (Cornell University)·2019· 2 citedOpen Access
A Generic Human–Machine Annotation Framework Based on Dynamic Cooperative Learning
IEEE Transactions on Cybernetics·2019· 21 citedOpen Access
Three recent trends in Paralinguistics on the way to omniscient machine intelligence
Journal on Multimodal User Interfaces·2018· 7 citedOpen Access
Single‐Channel Classification and Clustering Approaches
2018
Affective and behavioural computing: Lessons learnt from the First Computational Paralinguistics Challenge
Computer Speech & Language·2018· 50 citedOpen Access
A Paralinguistic Approach To Speaker Diarisation
2017· 9 citedOpen Access
page 1 of 7Next →

Frequent Co-authors

Björn W. Schuller(44), Florian Eyben(14), Gerhard Rigoll(11), Martin Wöllmer(10), Anton Batliner(9), Stefan Steidl(7), Jürgen T. Geiger(6), John R. Hershey(5), Jonathan Le Roux(5), Zixing Zhang(5), Alessandro Vinciarelli(4), Fabien Ringeval(4), Erik Marchi(4), Shinji Watanabe(4), Klaus R. Scherer(3), Marcello Mortillaro(3), Elmar Nöth(3), Felix Burkhardt(3), Benjamin Weiß(3), Simone Hantke(3)