R
Roland Maas
Researcher at Amazon.com
Publications - 74
Citations - 1964
Roland Maas is an academic researcher from Amazon.com. The author has contributed to research in topics: Hidden Markov model & Word error rate. The author has an hindex of 18, co-authored 68 publications receiving 1619 citations. Previous affiliations of Roland Maas include University of Erlangen-Nuremberg.
Papers
More filters
Proceedings ArticleDOI
The reverb challenge: Acommon evaluation framework for dereverberation and recognition of reverberant speech
Keisuke Kinoshita,Delcroix Marc,Takuya Yoshioka,Tomohiro Nakatani,Armin Sehr,Walter Kellermann,Roland Maas +6 more
TL;DR: A common evaluation framework including datasets, tasks, and evaluation metrics for both speech enhancement and ASR techniques is proposed, which will be used as a common basis for the REVERB (REverberant Voice Enhancement and Recognition Benchmark) challenge.
Journal ArticleDOI
A summary of the REVERB challenge: state-of-the-art and remaining challenges in reverberant speech processing research
Keisuke Kinoshita,Marc Delcroix,Sharon Gannot,Emanuel A. P. Habets,Reinhold Haeb-Umbach,Walter Kellermann,Volker Leutnant,Roland Maas,Tomohiro Nakatani,Bhiksha Raj,Armin Sehr,Takuya Yoshioka +11 more
TL;DR: The REVERB challenge is described, which is an evaluation campaign that was designed to evaluate such speech enhancement and ASR techniques to reveal the state-of-the-art techniques and obtain new insights regarding potential future research directions.
Journal ArticleDOI
Making Machines Understand Us in Reverberant Rooms: Robustness Against Reverberation for Automatic Speech Recognition
Takuya Yoshioka,Armin Sehr,Marc Delcroix,Keisuke Kinoshita,Roland Maas,Tomohiro Nakatani,Walter Kellermann +6 more
TL;DR: For a number of unexplored but important applications, distant microphones are a prerequisite for extending the availability of speech recognizers as well as enhancing the convenience of existing speech recognition applications.
Patent
Anchored speech detection and speech recognition
TL;DR: In this article, a system configured to process speech commands may classify incoming audio as desired speech, undesired speech, or non-speech, where desired speech is speech that is from a same speaker as reference speech.
Journal ArticleDOI
Reverberation Model-Based Decoding in the Logmelspec Domain for Robust Distant-Talking Speech Recognition
TL;DR: A novel reformulation of the constraint, which allows for an efficient solution by nonlinear optimization algorithms, is derived in this paper so that a practicable implementation of REMOS for logmelspec features becomes possible.