default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDRoland Maas
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
Books and Theses
- 2016
[b1]Roland Maas:
Uncertainty Decoding for Reverberation-Robust Automatic Speech Recognition. University of Erlangen-Nuremberg, Germany, 2016, ISBN 978-3-944057-61-3, pp. 1-191
Journal Articles
- 2018
- [j8]Christian Huemmer
, Christian Hofmann, Roland Maas, Walter Kellermann:
Estimating Parameters of Nonlinear Systems Using the Elitist Particle Filter Based on Evolutionary Strategies. IEEE ACM Trans. Audio Speech Lang. Process. 26(3): 595-608 (2018) - 2016
- [j7]Keisuke Kinoshita, Marc Delcroix, Sharon Gannot, Emanuël A. P. Habets, Reinhold Haeb-Umbach, Walter Kellermann, Volker Leutnant, Roland Maas, Tomohiro Nakatani, Bhiksha Raj, Armin Sehr, Takuya Yoshioka:
A summary of the REVERB challenge: state-of-the-art and remaining challenges in reverberant speech processing research. EURASIP J. Adv. Signal Process. 2016: 7 (2016) - 2015
- [j6]Christian Huemmer, Roland Maas, Christian Hofmann, Walter Kellermann:
A Bayesian network approach to linear and nonlinear acoustic echo cancellation. EURASIP J. Adv. Signal Process. 2015: 98 (2015) - [j5]Roland Maas, Christian Huemmer, Armin Sehr, Walter Kellermann:
A Bayesian view on acoustic model-based techniques for robust speech recognition. EURASIP J. Adv. Signal Process. 2015: 103 (2015) - [j4]Christian Huemmer, Roland Maas, Walter Kellermann:
The NLMS Algorithm with Time-Variant Optimum Stepsize Derived from a Bayesian Network Perspective. IEEE Signal Process. Lett. 22(11): 1874-1878 (2015) - 2013
- [j3]Klaus Reindl, Yuanhang Zheng, Andreas Schwarz, Stefan Meier, Roland Maas, Armin Sehr, Walter Kellermann:
A stereophonic acoustic signal extraction scheme for noisy and reverberant environments. Comput. Speech Lang. 27(3): 726-745 (2013) - 2012
- [j2]Takuya Yoshioka, Armin Sehr, Marc Delcroix, Keisuke Kinoshita, Roland Maas, Tomohiro Nakatani, Walter Kellermann:
Making Machines Understand Us in Reverberant Rooms: Robustness Against Reverberation for Automatic Speech Recognition. IEEE Signal Process. Mag. 29(6): 114-126 (2012) - 2010
- [j1]Armin Sehr, Roland Maas, Walter Kellermann:
Reverberation Model-Based Decoding in the Logmelspec Domain for Robust Distant-Talking Speech Recognition. IEEE Trans. Speech Audio Process. 18(7): 1676-1691 (2010)
Conference and Workshop Papers
- 2023
- [c44]Anirudh Raju, Aparna Khare, Di He, Ilya Sklyar, Long Chen, Sam Alptekin, Viet Anh Trinh, Zhe Zhang, Colin Vaz, Venkatesh Ravichandran, Roland Maas, Ariya Rastrow:
Two-Pass Endpoint Detection for Speech Recognition. ASRU 2023: 1-8 - [c43]Srinath Tankasala, Long Chen, Andreas Stolcke, Anirudh Raju, Qianli Deng, Chander Chandak, Aparna Khare, Roland Maas, Venkatesh Ravichandran:
Cross-Utterance ASR Rescoring with Graph-Based Label Propagation. ICASSP 2023: 1-5 - 2022
- [c42]Jinhan Wang, Xiaosu Tong, Jinxi Guo, Di He, Roland Maas:
VADOI: Voice-Activity-Detection Overlapping Inference for End-To-End Long-Form Speech Recognition. ICASSP 2022: 6977-6981 - [c41]Viet Anh Trinh, Pegah Ghahremani, Brian John King, Jasha Droppo, Andreas Stolcke, Roland Maas:
Reducing Geographic Disparities in Automatic Speech Recognition via Elastic Weight Consolidation. INTERSPEECH 2022: 1298-1302 - [c40]Phani Sankar Nidadavolu, Na Xu, Nick Jutila, Ravi Teja Gadde, Aswarth Abhilash Dara, Joseph Savold, Sapan Patel, Aaron Hoff, Veerdhawal Pande, Kevin Crews, Ankur Gandhe, Ariya Rastrow, Roland Maas:
RefTextLAS: Reference Text Biased Listen, Attend, and Spell Model For Accurate Reading Evaluation. INTERSPEECH 2022: 4347-4351 - [c39]Gokce Keskin, Minhua Wu, Brian John King, Sri Harish Mallidi, Yang Gao, Jasha Droppo, Ariya Rastrow, Roland Maas:
Do You Listen with one or two Microphones? A Unified ASR Model for Single and Multi-Channel Audio. IWAENC 2022: 1-5 - [c38]Aparna Khare, Minhua Wu, Saurabhchand Bhati, Jasha Droppo, Roland Maas:
Guided Contrastive Self-Supervised Pre-Training for Automatic Speech Recognition. SLT 2022: 174-181 - 2021
- [c37]Hu Hu, Xuesong Yang, Zeynab Raeesy, Jinxi Guo, Gokce Keskin, Harish Arsikere, Ariya Rastrow, Andreas Stolcke, Roland Maas:
REDAT: Accent-Invariant Representation for End-To-End ASR by Domain Adversarial Training with Relabeling. ICASSP 2021: 6408-6412 - [c36]Surabhi Punjabi, Harish Arsikere, Zeynab Raeesy, Chander Chandak, Nikhil Bhave, Ankish Bansal, Markus Müller, Sergio Murillo, Ariya Rastrow, Andreas Stolcke, Jasha Droppo, Sri Garimella, Roland Maas, Mat Hans, Athanasios Mouchtaris, Siegfried Kunzmann:
Joint ASR and Language Identification Using RNN-T: An Efficient Approach to Dynamic Language Switching. ICASSP 2021: 7218-7222 - [c35]Samik Sadhu, Di He, Che-Wei Huang, Sri Harish Mallidi, Minhua Wu, Ariya Rastrow, Andreas Stolcke, Jasha Droppo, Roland Maas:
wav2vec-C: A Self-Supervised Model for Speech Representation Learning. Interspeech 2021: 711-715 - [c34]Amin Fazel, Wei Yang, Yulan Liu, Roberto Barra-Chicote, Yixiong Meng, Roland Maas, Jasha Droppo:
SynthASR: Unlocking Synthetic Data for Speech Recognition. Interspeech 2021: 896-900 - [c33]Xiaosu Tong, Che-Wei Huang, Sri Harish Mallidi, Shaun Joseph, Sonal Pareek, Chander Chandak, Ariya Rastrow, Roland Maas:
Streaming ResLSTM with Causal Mean Aggregation for Device-Directed Utterance Detection. SLT 2021: 659-664 - 2020
- [c32]Maarten Van Segbroeck, Ahmed Zaid, Ksenia Kutsenko, Cirenia Huerta, Tinh Nguyen, Xuewen Luo, Björn Hoffmeister, Jan Trmal, Maurizio Omologo, Roland Maas:
DiPCo - Dinner Party Corpus. INTERSPEECH 2020: 434-436 - [c31]Jinxi Guo, Gautam Tiwari, Jasha Droppo, Maarten Van Segbroeck, Che-Wei Huang, Andreas Stolcke, Roland Maas:
Efficient Minimum Word Error Rate Training of RNN-Transducer for End-to-End Speech Recognition. INTERSPEECH 2020: 2807-2811 - 2019
- [c30]Ladislav Mosner, Minhua Wu, Anirudh Raju, Sree Hari Krishnan Parthasarathi, Ken'ichi Kumatani, Shiva Sundaram, Roland Maas, Björn Hoffmeister:
Improving Noise Robustness of Automatic Speech Recognition via Parallel Data and Teacher-student Learning. ICASSP 2019: 6475-6479 - [c29]Prakhar Swarup, Roland Maas, Sri Garimella, Sri Harish Mallidi, Björn Hoffmeister:
Improving ASR Confidence Scores for Alexa Using Acoustic and Hypothesis Embeddings. INTERSPEECH 2019: 2175-2179 - [c28]Che-Wei Huang, Roland Maas, Sri Harish Mallidi, Björn Hoffmeister:
A Study for Improving Device-Directed Speech Detection Toward Frictionless Human-Machine Interaction. INTERSPEECH 2019: 3342-3346 - 2018
- [c27]Roland Maas, Ariya Rastrow, Chengyuan Ma, Guitang Lan, Kyle Goehner, Gautam Tiwari, Shaun Joseph, Björn Hoffmeister:
Combining Acoustic Embeddings and Decoding Features for End-of-Utterance Detection in Real-Time Far-Field Speech Recognition Systems. ICASSP 2018: 5544-5548 - [c26]Sri Harish Reddy Mallidi, Roland Maas, Kyle Goehner, Ariya Rastrow, Spyros Matsoukas, Björn Hoffmeister:
Device-directed Utterance Detection. INTERSPEECH 2018: 1225-1228 - [c25]Zeynab Raeesy, Kellen Gillespie, Chengyuan Ma, Thomas Drugman, Jiacheng Gu, Roland Maas, Ariya Rastrow, Björn Hoffmeister:
LSTM-Based Whisper Detection. SLT 2018: 139-144 - 2017
- [c24]Roland Maas, Ariya Rastrow, Kyle Goehner, Gautam Tiwari, Shaun Joseph, Björn Hoffmeister:
Domain-Specific Utterance End-Point Detection for Speech Recognition. INTERSPEECH 2017: 1943-1947 - [c23]Brian John King, I-Fan Chen, Yonatan Vaizman, Yuzong Liu, Roland Maas, Sree Hari Krishnan Parthasarathi, Björn Hoffmeister:
Robust Speech Recognition via Anchor Word Representations. INTERSPEECH 2017: 2471-2475 - 2016
- [c22]Christian Huemmer, Andreas Schwarz, Roland Maas, Hendrik Barfuss, Ramón Fernandez Astudillo, Walter Kellermann:
A new uncertainty decoding scheme for DNN-HMM hybrid systems with multichannel speech enhancement. ICASSP 2016: 5760-5764 - [c21]Roland Maas, Sree Hari Krishnan Parthasarathi, Brian John King, Ruitong Huang, Björn Hoffmeister:
Anchored Speech Detection. INTERSPEECH 2016: 2963-2967 - 2015
- [c20]Andreas Schwarz, Christian Huemmer, Roland Maas, Walter Kellermann:
Spatial diffuseness features for DNN-based speech recognition in noisy and reverberant environments. ICASSP 2015: 4380-4384 - [c19]Christian Huemmer, Roland Maas, Andreas Schwarz, Ramón Fernandez Astudillo, Walter Kellermann:
Uncertainty decoding for DNN-HMM hybrid systems based on numerical sampling. INTERSPEECH 2015: 3556-3560 - [c18]Michael Buerger, Roland Maas, Heinrich W. Löllmann, Walter Kellermann:
Multizone sound field synthesis based on the joint optimization of the sound pressure and particle velocity vector on closed contours. WASPAA 2015: 1-5 - 2014
- [c17]Roland Maas, Christian Huemmer, Christian Hofmann, Walter Kellermann:
On Bayesian Networks in Speech Signal Processing. ITG Symposium on Speech Communication 2014: 1-4 - [c16]Roland Maas, Christian Huemmer, Andreas Schwarz, Christian Hofmann, Walter Kellermann:
A Bayesian network viewon linear and nonlinear acoustic echo cancellation. ChinaSIP 2014: 495-499 - [c15]Christian Huemmer, Christian Hofmann, Roland Maas, Walter Kellermann:
The significance-aware EPFES to estimate a memoryless preprocessor for nonlinear acoustic echo cancellation. GlobalSIP 2014: 557-561 - [c14]Armin Sehr, Hendrik Barfuss, Christian Hofmann, Roland Maas, Walter Kellermann:
Efficient training of acoustic models for reverberation-robust medium-vocabulary automatic speech recognition. HSCMA 2014: 177-181 - [c13]Christian Huemmer, Christian Hofmann, Roland Maas, Andreas Schwarz, Walter Kellermann:
The elitist particle filter based on evolutionary strategies as novel approach for nonlinear acoustic echo cancellation. ICASSP 2014: 1315-1319 - 2013
- [c12]Roland Maas, Akshaya Thippur, Armin Sehr, Walter Kellermann:
An uncertainty decoding approach to noise- and reverberation-robust speech recognition. ICASSP 2013: 7388-7392 - [c11]Roland Maas, Walter Kellermann, Armin Sehr, Takuya Yoshioka, Marc Delcroix, Keisuke Kinoshita, Tomohiro Nakatani:
Formulation of the REMOS concept from an uncertainty decoding perspective. DSP 2013: 1-6 - [c10]Armin Sehr, Takuya Yoshioka, Marc Delcroix, Keisuke Kinoshita, Tomohiro Nakatani, Roland Maas, Walter Kellermann:
Conditional emission densities for combining speech enhancement and recognition systems. INTERSPEECH 2013: 3502-3506 - [c9]Keisuke Kinoshita, Marc Delcroix, Takuya Yoshioka, Tomohiro Nakatani, Armin Sehr, Walter Kellermann, Roland Maas:
The reverb challenge: Acommon evaluation framework for dereverberation and recognition of reverberant speech. WASPAA 2013: 1-4 - 2012
- [c8]Takuya Yoshioka, Armin Sehr, Marc Delcroix, Keisuke Kinoshita, Roland Maas, Tomohiro Nakatani, Walter Kellermann:
Survey on approaches to speech recognition in reverberant environments. APSIPA 2012: 1-4 - [c7]Roland Maas, Sujan R. Kotha, Armin Sehr, Walter Kellermann:
Combined-order hidden Markov models for reverberation-robust speech recognition. CIP 2012: 1-5 - [c6]Roland Maas, Emanuël A. P. Habets, Armin Sehr, Walter Kellermann:
On the application of reverberation suppression to robust speech recognition. ICASSP 2012: 297-300 - 2011
- [c5]Armin Sehr, Roland Maas, Walter Kellermann:
Frame-wise HMM adaptation using state-dependent reverberation estimates. ICASSP 2011: 5484-5487 - 2010
- [c4]Roland Maas, Armin Sehr, Walter Kellermann:
Multi-Style Reverberation Models and Efficient Model Adaptation for Robust Distant-Talking Speech Recognition with REMOS. Sprachkommunikation 2010: 1-4 - [c3]Roland Maas, Armin Sehr, Martin Gugat, Walter Kellermann:
A highly efficient optimization scheme for REMOS-based distant-talking speech recognition. EUSIPCO 2010: 1983-1987 - [c2]Armin Sehr, Roland Maas, Walter Kellermann:
Model-based dereverberation in the logmelspec domain for robust distant-talking speech recognition. ICASSP 2010: 4298-4301 - [c1]Armin Sehr, Christian Hofmann, Roland Maas, Walter Kellermann:
A novel approach for matched reverberant training of HMMs using data pairs. INTERSPEECH 2010: 566-569
Parts in Books or Collections
- 2017
- [p1]Keisuke Kinoshita, Marc Delcroix, Sharon Gannot, Emanuël A. P. Habets, Reinhold Haeb-Umbach, Walter Kellermann, Volker Leutnant, Roland Maas, Tomohiro Nakatani, Bhiksha Raj, Armin Sehr, Takuya Yoshioka:
The REVERB Challenge: A Benchmark Task for Reverberation-Robust ASR Techniques. New Era for Robust Speech Recognition, Exploiting Deep Learning 2017: 345-354
Informal and Other Publications
- 2024
- [i21]Anirudh Raju, Aparna Khare, Di He, Ilya Sklyar, Long Chen, Sam Alptekin, Viet Anh Trinh, Zhe Zhang, Colin Vaz, Venkatesh Ravichandran, Roland Maas, Ariya Rastrow:
Two-pass Endpoint Detection for Speech Recognition. CoRR abs/2401.08916 (2024) - 2023
- [i20]Srinath Tankasala, Long Chen, Andreas Stolcke, Anirudh Raju, Qianli Deng, Chander Chandak, Aparna Khare, Roland Maas, Venkatesh Ravichandran:
Cross-utterance ASR Rescoring with Graph-based Label Propagation. CoRR abs/2303.15132 (2023) - 2022
- [i19]Jinhan Wang, Xiaosu Tong, Jinxi Guo, Di He, Roland Maas:
VADOI: Voice-Activity-Detection Overlapping Inference For End-to-end Long-form Speech Recognition. CoRR abs/2202.10593 (2022) - [i18]Viet Anh Trinh, Pegah Ghahremani, Brian John King, Jasha Droppo, Andreas Stolcke, Roland Maas:
Reducing Geographic Disparities in Automatic Speech Recognition via Elastic Weight Consolidation. CoRR abs/2207.07850 (2022) - [i17]Aparna Khare, Minhua Wu, Saurabhchand Bhati, Jasha Droppo, Roland Maas:
Guided contrastive self-supervised pre-training for automatic speech recognition. CoRR abs/2210.12335 (2022) - 2021
- [i16]Samik Sadhu, Di He, Che-Wei Huang, Sri Harish Mallidi, Minhua Wu, Ariya Rastrow, Andreas Stolcke, Jasha Droppo, Roland Maas:
Wav2vec-C: A Self-supervised Model for Speech Representation Learning. CoRR abs/2103.08393 (2021) - [i15]Bhargav Pulugundla, Yang Gao, Brian John King, Gokce Keskin, Sri Harish Mallidi, Minhua Wu, Jasha Droppo, Roland Maas:
Attention-based Neural Beamforming Layers for Multi-channel Speech Recognition. CoRR abs/2105.05920 (2021) - [i14]Gokce Keskin, Minhua Wu, Brian John King, Sri Harish Mallidi, Yang Gao, Jasha Droppo, Ariya Rastrow, Roland Maas:
Do You Listen with One or Two Microphones? A Unified ASR Model for Single and Multi-Channel Audio. CoRR abs/2106.02750 (2021) - [i13]Amin Fazel, Wei Yang, Yulan Liu, Roberto Barra-Chicote, Yixiong Meng, Roland Maas, Jasha Droppo:
SynthASR: Unlocking Synthetic Data for Speech Recognition. CoRR abs/2106.07803 (2021) - 2020
- [i12]Chander Chandak, Zeynab Raeesy, Ariya Rastrow, Yuzong Liu, Xiangyang Huang, Siyu Wang, Dong Kwon Joo, Roland Maas:
Streaming Language Identification using Combination of Acoustic Representations and ASR Hypotheses. CoRR abs/2006.00703 (2020) - [i11]Maarten Van Segbroeck, Sri Harish Mallidi, Brian John King, I-Fan Chen, Gurpreet Chadha, Roland Maas:
Multi-view Frequency LSTM: An Efficient Frontend for Automatic Speech Recognition. CoRR abs/2007.00131 (2020) - [i10]Surabhi Punjabi, Harish Arsikere, Zeynab Raeesy, Chander Chandak, Nikhil Bhave, Ankish Bansal, Markus Müller, Sergio Murillo, Ariya Rastrow, Sri Garimella, Roland Maas, Mat Hans, Athanasios Mouchtaris, Siegfried Kunzmann:
Streaming End-to-End Bilingual ASR Systems with Joint Language Identification. CoRR abs/2007.03900 (2020) - [i9]Xiaosu Tong, Che-Wei Huang, Sri Harish Mallidi, Shaun Joseph, Sonal Pareek, Chander Chandak, Ariya Rastrow, Roland Maas:
Streaming ResLSTM with Causal Mean Aggregation for Device-Directed Utterance Detection. CoRR abs/2007.09245 (2020) - [i8]Jinxi Guo, Gautam Tiwari, Jasha Droppo, Maarten Van Segbroeck, Che-Wei Huang, Andreas Stolcke, Roland Maas:
Efficient minimum word error rate training of RNN-Transducer for end-to-end speech recognition. CoRR abs/2007.13802 (2020) - [i7]Hu Hu, Xuesong Yang, Zeynab Raeesy, Jinxi Guo, Gökçe Keskin, Harish Arsikere, Ariya Rastrow, Andreas Stolcke, Roland Maas:
REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabeling. CoRR abs/2012.07353 (2020) - 2019
- [i6]Ladislav Mosner, Minhua Wu, Anirudh Raju, Sree Hari Krishnan Parthasarathi, Ken'ichi Kumatani, Shiva Sundaram, Roland Maas, Björn Hoffmeister:
Improving noise robustness of automatic speech recognition via parallel data and teacher-student learning. CoRR abs/1901.02348 (2019) - [i5]Maarten Van Segbroeck, Ahmed Zaid, Ksenia Kutsenko, Cirenia Huerta, Tinh Nguyen, Xuewen Luo, Björn Hoffmeister, Jan Trmal, Maurizio Omologo, Roland Maas:
DiPCo - Dinner Party Corpus. CoRR abs/1909.13447 (2019) - 2018
- [i4]Sri Harish Reddy Mallidi, Roland Maas, Kyle Goehner, Ariya Rastrow, Spyros Matsoukas, Björn Hoffmeister:
Device-directed Utterance Detection. CoRR abs/1808.02504 (2018) - [i3]Zeynab Raeesy, Kellen Gillespie, Chengyuan Ma, Thomas Drugman, Jiacheng Gu, Roland Maas, Ariya Rastrow, Björn Hoffmeister:
LSTM-based Whisper Detection. CoRR abs/1809.07832 (2018) - 2014
- [i2]Andreas Schwarz, Christian Huemmer, Roland Maas, Walter Kellermann:
Spatial Diffuseness Features for DNN-Based Speech Recognition in Noisy and Reverberant Environments. CoRR abs/1410.2479 (2014) - 2013
- [i1]Roland Maas, Christian Huemmer, Armin Sehr, Walter Kellermann:
A Bayesian Network View on Acoustic Model-Based Techniques for Robust Speech Recognition. CoRR abs/1310.3099 (2013)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-10-07 22:15 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
