Niko Moritz

发表

An Investigation of Monotonic Transducers for Large-Scale Automatic Speech Recognition

F. Seide, Niko Moritz, Duc Le, 2022, 2204.08858.

Information and communication technologies for promoting and sustaining quality of life, health and self-sufficiency in ageing societies – outcomes of the Lower Saxony Research Network Design of Environments for Ageing (GAL)

Jürgen M Bauer, Wolfgang Nebel, Axel Helmer, 2014, Informatics for health & social care.

Challenge on Detection and Classification of Acoustic Scenes and Events ACOUSTIC EVENT DETECTION USING SIGNAL ENHANCEMENT AND SPECTRO-TEMPORAL FEATURE EXTRACTION

B. Kollmeier, S. Doclo, K. Adiloglu, 2013 .

Semi-Supervised Speech Recognition Via Graph-Based Temporal Classification pdf

Jonathan Le Roux, Takaaki Hori, Niko Moritz, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Time and Frequency Domain SONAR Beamforming in the Near-Field by Niko Moritz

Niko Moritz, 2007 .

Transgenic Mice Overexpressing Neuropeptide Y in Noradrenergic Neurons

M. Koulu, U. Pesonen, E. Savontaus, 2008, Diabetes.

Anchored Speech Recognition with Neural Transducers

Xiaohui Zhang, Ozlem Kalinli, J. Jia, 2022, ArXiv.

Momentum Pseudo-Labeling: Semi-Supervised ASR With Continuously Improving Pseudo-Labels

Takaaki Hori, J. Le Roux, Niko Moritz, 2022, IEEE Journal of Selected Topics in Signal Processing.

An Auditory Inspired Amplitude Modulation Filter Bank for Robust Feature Extraction in Automatic Speech Recognition

Birger Kollmeier, Niko Moritz, Jörn Anemüller, 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Classifier Architectures for Acoustic Scenes and Events: Implications for DNNs, TDNNs, and Perceptual Features from DCASE 2016

Birger Kollmeier, Niko Moritz, Jörn Anemüller, 2017, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition pdf

Takaaki Hori, Niko Moritz, Yosuke Higuchi, 2021, Interspeech.

Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy pdf

Takaaki Hori, Niko Moritz, Jonathan Le Roux, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Transformer-Based Long-Context End-to-End Speech Recognition

Jonathan Le Roux, Chiori Hori, Takaaki Hori, 2020, INTERSPEECH.

Triggered Attention for End-to-end Speech Recognition

Jonathan Le Roux, Takaaki Hori, Niko Moritz, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Extended Graph Temporal Classification for Multi-Speaker End-to-End ASR

Jonathan Le Roux, Takaaki Hori, Shinji Watanabe, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Streaming Automatic Speech Recognition with the Transformer Model

Jonathan Le Roux, Takaaki Hori, Niko Moritz, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multi-Channel Speech Enhancement and Amplitude Modulation Analysis for Noise Robust Automatic Speech Recognition

Birger Kollmeier, Kamil Adiloglu, Jörn Anemüller, 2017, Comput. Speech Lang..

Semi-Supervised Speech Recognition Via Graph-Based Temporal Classification

Jonathan Le Roux, Takaaki Hori, Niko Moritz, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

SynthVSR: Scaling Up Visual Speech RecognitionWith Synthetic Supervision

M. Pantic, Niko Moritz, Christian Fuegen, 2023, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Streaming Audio-Visual Speech Recognition with Alignment Regularization

M. Pantic, Niko Moritz, Christian Fuegen, 2022, arXiv.org.

Streaming End-to-End Speech Recognition with Joint CTC-Attention Based Models

Jonathan Le Roux, Takaaki Hori, Niko Moritz, 2019, 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

NOISE ROBUST DISTANT AUTOMATIC SPEECH RECOGNITION UTILIZING NMF BASED SOURCE SEPARATION AND AUDITORY FEATURE EXTRACTION

Tim Jürgens, Birger Kollmeier, Marc René Schädler, 2013 .

Sequence Transduction with Graph-Based Supervision

Jonathan Le Roux, Takaaki Hori, Shinji Watanabe, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformers pdf

Takaaki Hori, Chiori Hori, Niko Moritz, 2021, Interspeech.

Anchored Speech Recognition with Neural Transducers

Xiaohui Zhang, Ozlem Kalinli, J. Jia, 2022, IEEE International Conference on Acoustics, Speech, and Signal Processing.

Dual Causal/Non-Causal Self-Attention for Streaming End-to-End Speech Recognition pdf

Takaaki Hori, Niko Moritz, Jonathan Le Roux, 2021, Interspeech.

Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training

Jonathan Le Roux, Takaaki Hori, Sameer Khurana, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Vectorized Beam Search for CTC-Attention-Based Speech Recognition

Jonathan Le Roux, Shinji Watanabe, Takaaki Hori, 2019, INTERSPEECH.

Robust ASR in Reverberant Environments using Temporal Cepstrum Smoothing for Speech Enhancement and an Amplitude Modulation Filterbank for Feature Extraction

Niko Moritz, Stefan Goetze, Bernd T. Meyer, 2014 .

Front-end technologies for robust ASR in reverberant environments—spectral enhancement-based dereverberation and auditory modulation filterbank features

S. Doclo, Timo Gerkmann, B. Meyer, 2015, EURASIP J. Adv. Signal Process..

Amplitude modulation spectrogram based features for robust speech recognition in noisy and reverberant environments

Birger Kollmeier, Niko Moritz, Jörn Anemüller, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Unsupervised Speaker Adaptation Using Attention-Based Speaker Memory for End-to-End ASR

Jonathan Le Roux, Takaaki Hori, Leda Sari, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Streaming Audio-Visual Speech Recognition with Alignment Regularization

M. Pantic, Niko Moritz, Christian Fuegen, 2022, arXiv.org.

All-in-One Transformer: Unifying Speech Recognition, Audio Tagging, and Event Detection

Jonathan Le Roux, Takaaki Hori, Gordon Wichern, 2020, INTERSPEECH.

Capturing Multi-Resolution Context by Dilated Self-Attention

Takaaki Hori, Niko Moritz, Jonathan Le Roux, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Three-Stage Gradient-Based Optimization Scheme in Design of Feedback Gains within Eurofighter Primary Control Laws

Nikolaus Moritz, Robert Osterhuber, Niko Moritz, 2006 .

Acoustic user interfaces for ambient-assisted living technologies

Niko Moritz, Stefan Goetze, Markus Meis, 2010, Informatics for health & social care.

On sound source localization of speech signals using deep neural networks

Stephan Gerlach, Stefan Goetze, Stefan Weinzierl, 2015 .

Multimodal Human-Machine Interaction for Service Robots in Home-Care Environments

Niko Moritz, Stefan Goetze, Sven Fischer, 2012, SMIAE@ACL.

Acoustic user interfaces for ambient-assisted living technologies

Stefan Goetze, Jörg Bitzer, Jens-E. Appell, 2010, Informatics for health & social care.

Streaming Audio-Visual Speech Recognition with Alignment Regularization

M. Pantic, Niko Moritz, Christian Fuegen, 2022, INTERSPEECH 2023.