Search Results for author: Reinhold Haeb-Umbach

Found 26 papers, 12 papers with code

MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator

1 code implementation23 Sep 2022 Tobias Cord-Landwehr, Thilo von Neumann, Christoph Boeddeker, Reinhold Haeb-Umbach

Training and evaluation of these single tasks requires synthetic data with access to intermediate signals that is as close as possible to the evaluation scenario.

Speech Enhancement

Investigation into Target Speaking Rate Adaptation for Voice Conversion

no code implementations5 Sep 2022 Michael Kuhlmann, Fritz Seebauer, Janek Ebbers, Petra Wagner, Reinhold Haeb-Umbach

Disentangling speaker and content attributes of a speech signal into separate latent representations followed by decoding the content with an exchanged speaker representation is a popular approach for voice conversion, which can be trained with non-parallel and unlabeled speech data.

Disentanglement Voice Conversion

Utterance-by-utterance overlap-aware neural diarization with Graph-PIT

1 code implementation28 Jul 2022 Keisuke Kinoshita, Thilo von Neumann, Marc Delcroix, Christoph Boeddeker, Reinhold Haeb-Umbach

In this paper, we argue that such an approach involving the segmentation has several issues; for example, it inevitably faces a dilemma that larger segment sizes increase both the context available for enhancing the performance and the number of speakers for the local EEND module to handle.

speaker-diarization Speaker Diarization

A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network

no code implementations2 May 2022 Tobias Gburrek, Christoph Boeddeker, Thilo von Neumann, Tobias Cord-Landwehr, Joerg Schmalenstroeer, Reinhold Haeb-Umbach

We propose a system that transcribes the conversation of a typical meeting scenario that is captured by a set of initially unsynchronized microphone arrays at unknown positions.

Automatic Speech Recognition Speech Enhancement +1

Threshold Independent Evaluation of Sound Event Detection Scores

1 code implementation31 Jan 2022 Janek Ebbers, Romain Serizel, Reinhold Haeb-Umbach

Performing an adequate evaluation of sound event detection (SED) systems is far from trivial and is still subject to ongoing research.

Event Detection Sound Event Detection

Monaural source separation: From anechoic to reverberant environments

no code implementations15 Nov 2021 Tobias Cord-Landwehr, Christoph Boeddeker, Thilo von Neumann, Catalin Zorila, Rama Doddipatla, Reinhold Haeb-Umbach

Impressive progress in neural network-based single-channel speech source separation has been made in recent years.

SA-SDR: A novel loss function for separation of meeting style data

no code implementations29 Oct 2021 Thilo von Neumann, Keisuke Kinoshita, Christoph Boeddeker, Marc Delcroix, Reinhold Haeb-Umbach

Many state-of-the-art neural network-based source separation systems use the averaged Signal-to-Distortion Ratio (SDR) as a training objective function.

On Synchronization of Wireless Acoustic Sensor Networks in the Presence of Time-varying Sampling Rate Offsets and Speaker Changes

1 code implementation25 Oct 2021 Tobias Gburrek, Joerg Schmalenstroeer, Reinhold Haeb-Umbach

A wireless acoustic sensor network records audio signals with sampling time and sampling rate offsets between the audio streams, if the analog-digital converters (ADCs) of the network devices are not synchronized.

Speeding Up Permutation Invariant Training for Source Separation

1 code implementation30 Jul 2021 Thilo von Neumann, Christoph Boeddeker, Keisuke Kinoshita, Marc Delcroix, Reinhold Haeb-Umbach

The Hungarian algorithm can be used for uPIT and we introduce various algorithms for the Graph-PIT assignment problem to reduce the complexity to be polynomial in the number of utterances.

Graph-PIT: Generalized permutation invariant training for continuous separation of arbitrary numbers of speakers

1 code implementation30 Jul 2021 Thilo von Neumann, Keisuke Kinoshita, Christoph Boeddeker, Marc Delcroix, Reinhold Haeb-Umbach

When processing meeting-like data in a segment-wise manner, i. e., by separating overlapping segments independently and stitching adjacent segments to continuous output streams, this constraint has to be fulfilled for any segment.

Speech Separation

Warping of Radar Data into Camera Image for Cross-Modal Supervision in Automotive Applications

no code implementations23 Dec 2020 Christopher Grimm, Tai Fei, Ernst Warsitz, Ridha Farhoud, Tobias Breddermann, Reinhold Haeb-Umbach

As the warping operation relies on accurate scene flow estimation, we further propose a novel scene flow estimation algorithm which exploits information from camera, lidar and radar sensors.

Direction of Arrival Estimation Object Recognition +2

Iterative Geometry Calibration from Distance Estimates for Wireless Acoustic Sensor Networks

1 code implementation11 Dec 2020 Tobias Gburrek, Joerg Schmalenstroeer, Reinhold Haeb-Umbach

In this paper we present an approach to geometry calibration in wireless acoustic sensor networks, whose nodes are assumed to be equipped with a compact microphone array.

Multi-talker ASR for an unknown number of sources: Joint training of source counting, separation and ASR

no code implementations4 Jun 2020 Thilo von Neumann, Christoph Boeddeker, Lukas Drude, Keisuke Kinoshita, Marc Delcroix, Tomohiro Nakatani, Reinhold Haeb-Umbach

Most approaches to multi-talker overlapped speech separation and recognition assume that the number of simultaneously active speakers is given, but in realistic situations, it is typically unknown.

Automatic Speech Recognition Speech Extraction +1

End-to-end training of time domain audio separation and recognition

no code implementations18 Dec 2019 Thilo von Neumann, Keisuke Kinoshita, Lukas Drude, Christoph Boeddeker, Marc Delcroix, Tomohiro Nakatani, Reinhold Haeb-Umbach

The rising interest in single-channel multi-speaker speech separation sparked development of End-to-End (E2E) approaches to multi-speaker speech recognition.

Speaker Recognition speech-recognition +2

Demystifying TasNet: A Dissecting Approach

no code implementations20 Nov 2019 Jens Heitkaemper, Darius Jakobeit, Christoph Boeddeker, Lukas Drude, Reinhold Haeb-Umbach

In recent years time domain speech separation has excelled over frequency domain separation in single channel scenarios and noise-free environments.

Speech Separation

SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition

3 code implementations30 Oct 2019 Lukas Drude, Jens Heitkaemper, Christoph Boeddeker, Reinhold Haeb-Umbach

We present a multi-channel database of overlapping speech for training, evaluation, and detailed analysis of source separation and extraction algorithms: SMS-WSJ -- Spatialized Multi-Speaker Wall Street Journal.

Jointly optimal dereverberation and beamforming

no code implementations30 Oct 2019 Christoph Boeddeker, Tomohiro Nakatani, Keisuke Kinoshita, Reinhold Haeb-Umbach

We previously proposed an optimal (in the maximum likelihood sense) convolutional beamformer that can perform simultaneous denoising and dereverberation, and showed its superiority over the widely used cascade of a WPE dereverberation filter and a conventional MPDR beamformer.

Denoising

An Investigation into the Effectiveness of Enhancement in ASR Training and Test for CHiME-5 Dinner Party Transcription

1 code implementation26 Sep 2019 Catalin Zorila, Christoph Boeddeker, Rama Doddipatla, Reinhold Haeb-Umbach

Despite the strong modeling power of neural network acoustic models, speech enhancement has been shown to deliver additional word error rate improvements if multi-channel data is available.

Speech Enhancement

Unsupervised training of neural mask-based beamforming

no code implementations2 Apr 2019 Lukas Drude, Jahn Heymann, Reinhold Haeb-Umbach

In contrast to previous work on unsupervised training of neural mask estimators, our approach avoids the need for a possibly pre-trained teacher model entirely.

speech-recognition Speech Recognition

Unsupervised training of a deep clustering model for multichannel blind source separation

no code implementations2 Apr 2019 Lukas Drude, Daniel Hasenklever, Reinhold Haeb-Umbach

We propose a training scheme to train neural network-based source separation algorithms from scratch when parallel clean data is unavailable.

Deep Clustering Unsupervised Spatial Clustering

All-neural online source separation, counting, and diarization for meeting analysis

no code implementations21 Feb 2019 Thilo von Neumann, Keisuke Kinoshita, Marc Delcroix, Shoko Araki, Tomohiro Nakatani, Reinhold Haeb-Umbach

While significant progress has been made on individual tasks, this paper presents for the first time an all-neural approach to simultaneous speaker counting, diarization and source separation.

Automatic Speech Recognition speaker-diarization +2

Directional Statistics and Filtering Using libDirectional

no code implementations28 Dec 2017 Gerhard Kurz, Igor Gilitschenski, Florian Pfaff, Lukas Drude, Uwe D. Hanebeck, Reinhold Haeb-Umbach, Roland Y. Siegwart

In this paper, we present libDirectional, a MATLAB library for directional statistics and directional estimation.

Cannot find the paper you are looking for? You can Submit a new open access paper.