Brecht Desplanques
YOU?
Author Swipe
Post-Training Embedding Alignment for Decoupling Enrollment and Runtime Speaker Recognition Models Open
Automated speaker identification (SID) is a crucial step for the personalization of a wide range of speech-enabled services. Typical SID systems use a symmetric enrollment-verification framework with a single model to derive embeddings bot…
Tackling the Score Shift in Cross-Lingual Speaker Verification by Exploiting Language Information Open
This paper contains a post-challenge performance analysis on cross-lingual\nspeaker verification of the IDLab submission to the VoxCeleb Speaker\nRecognition Challenge 2021 (VoxSRC-21). We show that current speaker embedding\nextractors co…
Robust Acoustic Scene Classification in thePresence of Active Foreground Speech Open
We present an iVector based Acoustic Scene Clas-sification (ASC) system suited for real life settings where activeforeground speech can be present. In the proposed system, eachrecording is represented by a fixed-length iVector that modelst…
The IDLAB VoxCeleb Speaker Recognition Challenge 2021 System Description Open
This technical report describes the IDLab submission for track 1 and 2 of the VoxCeleb Speaker Recognition Challenge 2021 (VoxSRC-21). This speaker verification competition focuses on short duration test recordings and cross-lingual trials…
Integrating Frequency Translational Invariance in TDNNs and Frequency Positional Information in 2D ResNets to Enhance Speaker Verification Open
This paper describes the IDLab submission for the text-independent task of the Short-duration Speaker Verification Challenge 2021 (SdSVC-21). This speaker verification competition focuses on short duration test recordings and cross-lingual…
ECAPA-TDNN Embeddings for Speaker Diarization Open
Learning robust speaker embeddings is a crucial step in speaker diarization.\nDeep neural networks can accurately capture speaker discriminative\ncharacteristics and popular deep embeddings such as x-vectors are nowadays a\nfundamental com…
Robust Acoustic Scene Classification in the Presence of Active Foreground Speech Open
We present an iVector based Acoustic Scene Classification (ASC) system suited for real life settings where active foreground speech can be present. In the proposed system, each recording is represented by a fixed-length iVector that models…
Robust Acoustic Scene Classification in the Presence of Active Foreground Speech Open
We present an iVector based Acoustic Scene Classification (ASC) system suited for real life settings where active foreground speech can be present. In the proposed system, each recording is represented by a fixed-length iVector that models…
The Idlab Voxsrc-20 Submission: Large Margin Fine-Tuning and Quality-Aware Score Calibration in DNN Based Speaker Verification Open
In this paper we propose and analyse a large margin fine-tuning strategy and\na quality-aware score calibration in text-independent speaker verification.\nLarge margin fine-tuning is a secondary training stage for DNN based speaker\nverifi…
View article: ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification
ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification Open
Current speaker verification techniques rely on a neural network to extract\nspeaker representations. The successful x-vector architecture is a Time Delay\nNeural Network (TDNN) that applies statistics pooling to project\nvariable-length u…
Cross-Lingual Speaker Verification with Domain-Balanced Hard Prototype Mining and Language-Dependent Score Normalization Open
In this paper we describe the top-scoring IDLab submission for the\ntext-independent task of the Short-duration Speaker Verification (SdSV)\nChallenge 2020. The main difficulty of the challenge exists in the large degree\nof varying phonet…
Cross-lingual Speech Emotion Recognition through Factor Analysis Open
Conventional speech emotion recognition based on the extraction of high level descriptors emerging from low level descriptors seldom delivers promising results in cross-corpus experiments.Therefore it might not perform well in real-life ap…
TTNWW to the Rescue: No Need to Know How to Handle Tools and Resources Open
‘But I don’t know how to work with [name of tool or resource]’ is something one often hears when researchers in Human and Social Sciences (HSS) are confronted with language technology, be it written or spoken, tools or resources. The TTNWW…
STON: Efficient subtitling in Dutch using state-of-the-art tools Open
Copyright © 2016 ISCA. We present a modular video subtitling platform that integrates speech/non-speech segmentation, speaker diarisation, language identification, Dutch speech recognition with state-of-the-art acoustic models and language…