Search Results for author: Hervé Bredin

Found 12 papers, 10 papers with code

Analyzing BERT Cross-lingual Transfer Capabilities in Continual Sequence Labeling

1 code implementation MMMPIE (COLING) 2022 Juan Manuel Coria, Mathilde Veron, Sahar Ghannay, Guillaume Bernard, Hervé Bredin, Olivier Galibert, Sophie Rosset

Knowledge transfer between neural language models is a widely used technique that has proven to improve performance in a multitude of natural language tasks, in particular with the recent rise of large pre-trained language models like BERT.

Continual Learning Cross-Lingual Transfer +6

Overlap-aware low-latency online speaker diarization based on end-to-end local segmentation

1 code implementation14 Sep 2021 Juan M. Coria, Hervé Bredin, Sahar Ghannay, Sophie Rosset

We propose to address online speaker diarization as a combination of incremental clustering and local diarization applied to a rolling buffer updated every 500ms.

speaker-diarization Speaker Diarization

End-to-end speaker segmentation for overlap-aware resegmentation

2 code implementations8 Apr 2021 Hervé Bredin, Antoine Laurent

Experiments on multiple speaker diarization datasets conclude that our model can be used with great success on both voice activity detection and overlapped speech detection.

Action Detection Activity Detection +4

An open-source voice type classifier for child-centered daylong recordings

1 code implementation26 May 2020 Marvin Lavechin, Ruben Bousbib, Hervé Bredin, Emmanuel Dupoux, Alejandrina Cristia

Spontaneous conversations in real-world settings such as those found in child-centered recordings have been shown to be amongst the most challenging audio files to process.

Language Acquisition

A Comparison of Metric Learning Loss Functions for End-To-End Speaker Verification

1 code implementation31 Mar 2020 Juan M. Coria, Hervé Bredin, Sahar Ghannay, Sophie Rosset

Despite the growing popularity of metric learning approaches, very little work has attempted to perform a fair comparison of these techniques for speaker verification.

Metric Learning Speaker Verification

End-to-end Domain-Adversarial Voice Activity Detection

1 code implementation23 Oct 2019 Marvin Lavechin, Marie-Philippe Gill, Ruben Bousbib, Hervé Bredin, Leibny Paola Garcia-Perera

In the in-domain scenario where the training and test sets cover the exact same domains, we show that the domain-adversarial approach does not degrade performance of the proposed end-to-end model.

Audio and Speech Processing I.2.7

LSTM based Similarity Measurement with Spectral Clustering for Speaker Diarization

1 code implementation23 Jul 2019 Qingjian Lin, Ruiqing Yin, Ming Li, Hervé Bredin, Claude Barras

More and more neural network approaches have achieved considerable improvement upon submodules of speaker diarization system, including speaker change detection and segment-wise speaker embedding extraction.

Change Detection speaker-diarization +1

TristouNet: Triplet Loss for Speaker Turn Embedding

6 code implementations14 Sep 2016 Hervé Bredin

TristouNet is a neural network architecture based on Long Short-Term Memory recurrent networks, meant to project speech sequences into a fixed-dimensional euclidean space.

Change Detection

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