Search Results for author:
Found 40 papers, 16 papers with code
Neural network based spectral mask estimation for acoustic beamforming
The network training is independent of the number and the geometric configuration of the microphones.
Guided Source Separation Meets a Strong ASR Backend: Hitachi/Paderborn University Joint Investigation for Dinner Party ASR
In this paper, we present Hitachi and Paderborn University's joint effort for automatic speech recognition (ASR) in a dinner party scenario.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
An Investigation into the Effectiveness of Enhancement in ASR Training and Test for CHiME-5 Dinner Party Transcription
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.
SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition
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.
Forward-Backward Convolutional Recurrent Neural Networks and Tag-Conditioned Convolutional Neural Networks for Weakly Labeled Semi-supervised Sound Event Detection
It is trained to predict strong labels while using (predicted) tags, i. e., weak labels, as additional input.
On Word Error Rate Definitions and their Efficient Computation for Multi-Speaker Speech Recognition Systems
We propose a general framework to compute the word error rate (WER) of ASR systems that process recordings containing multiple speakers at their input and that produce multiple output word sequences (MIMO).
MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems
MeetEval is an open-source toolkit to evaluate all kinds of meeting transcription systems.
MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator
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.
Graph-PIT: Generalized permutation invariant training for continuous separation of arbitrary numbers of speakers
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.
Speeding Up Permutation Invariant Training for Source Separation
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.
Utterance-by-utterance overlap-aware neural diarization with Graph-PIT
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.
Threshold Independent Evaluation of Sound Event Detection Scores
Performing an adequate evaluation of sound event detection (SED) systems is far from trivial and is still subject to ongoing research.
Post-Processing Independent Evaluation of Sound Event Detection Systems
It summarizes the system performance over a range of operating modes resulting from varying the decision threshold that is used to translate the system output scores into a binary detection output.
Iterative Geometry Calibration from Distance Estimates for Wireless Acoustic Sensor Networks
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.
On Synchronization of Wireless Acoustic Sensor Networks in the Presence of Time-varying Sampling Rate Offsets and Speaker Changes
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.
LibriWASN: A Data Set for Meeting Separation, Diarization, and Recognition with Asynchronous Recording Devices
We present LibriWASN, a data set whose design follows closely the LibriCSS meeting recognition data set, with the marked difference that the data is recorded with devices that are randomly positioned on a meeting table and whose sampling clocks are not synchronized.
Directional Statistics and Filtering Using libDirectional
In this paper, we present libDirectional, a MATLAB library for directional statistics and directional estimation.
All-neural online source separation, counting, and diarization for meeting analysis
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
Automatic Speech Recognition (ASR)
+3
Unsupervised training of a deep clustering model for multichannel blind source separation
We propose a training scheme to train neural network-based source separation algorithms from scratch when parallel clean data is unavailable.
Unsupervised training of neural mask-based beamforming
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.
Jointly optimal dereverberation and beamforming
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.
Demystifying TasNet: A Dissecting Approach
In recent years time domain speech separation has excelled over frequency domain separation in single channel scenarios and noise-free environments.
End-to-end training of time domain audio separation and recognition
The rising interest in single-channel multi-speaker speech separation sparked development of End-to-End (E2E) approaches to multi-speaker speech recognition.
Multi-talker ASR for an unknown number of sources: Joint training of source counting, separation and ASR
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
Automatic Speech Recognition (ASR)
+2
Warping of Radar Data into Camera Image for Cross-Modal Supervision in Automotive Applications
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.
End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend
Recently, the end-to-end approach has been successfully applied to multi-speaker speech separation and recognition in both single-channel and multichannel conditions.
SA-SDR: A novel loss function for separation of meeting style data
Many state-of-the-art neural network-based source separation systems use the averaged Signal-to-Distortion Ratio (SDR) as a training objective function.
Monaural source separation: From anechoic to reverberant environments
Impressive progress in neural network-based single-channel speech source separation has been made in recent years.
A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network
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
Automatic Speech Recognition (ASR)
+3
Investigation into Target Speaking Rate Adaptation for Voice Conversion
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.
TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings
Since diarization and source separation of meeting data are closely related tasks, we here propose an approach to perform the two objectives jointly.
Ranked #1 on
Speech Recognition
on LibriCSS
(using extra training data)
A Teacher-Student approach for extracting informative speaker embeddings from speech mixtures
We introduce a monaural neural speaker embeddings extractor that computes an embedding for each speaker present in a speech mixture.
Frame-wise and overlap-robust speaker embeddings for meeting diarization
Using a Teacher-Student training approach we developed a speaker embedding extraction system that outputs embeddings at frame rate.
Mixture Encoder for Joint Speech Separation and Recognition
Modular approaches separate speakers and recognize each of them with a single-speaker ASR system.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Investigating Speaker Embedding Disentanglement on Natural Read Speech
To quantify disentanglement, we identify acoustic features that are highly speaker-variant and can serve as proxies for the factors of variation underlying speech.
Mixture Encoder Supporting Continuous Speech Separation for Meeting Recognition
This mixture encoder leverages the original overlapped speech to mitigate the effect of artifacts introduced by the speech separation.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization
We propose a modular pipeline for the single-channel separation, recognition, and diarization of meeting-style recordings and evaluate it on the Libri-CSS dataset.
On Feature Importance and Interpretability of Speaker Representations
Unsupervised speech disentanglement aims at separating fast varying from slowly varying components of a speech signal.
Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks
We propose a diarization system, that estimates "who spoke when" based on spatial information, to be used as a front-end of a meeting transcription system running on the signals gathered from an acoustic sensor network (ASN).
Geodesic interpolation of frame-wise speaker embeddings for the diarization of meeting scenarios
We propose a modified teacher-student training for the extraction of frame-wise speaker embeddings that allows for an effective diarization of meeting scenarios containing partially overlapping speech.
