44 citations · 100 across the 34 of their papers we have counts for
29 papers · 1 filter
Target Speaker ASR with Whisper
Alexander Polok, Dominik Klement, Matthew Wiesner +3
We propose a novel approach to enable the use of large, single-speaker ASR models, such as Whisper, for target speaker ASR. The key claim of this method is that it is much easier t…
Multi-Stream Extension of Variational Bayesian HMM Clustering (MS-VBx) for Combined End-to-End and Vector Clustering-based Diarization
Marc Delcroix, Naohiro Tawara, Mireia Diez +6
Combining end-to-end neural speaker diarization (EEND) with vector clustering (VC), known as EEND-VC, has gained interest for leveraging the strengths of both methods. EEND-VC esti…
Speech-based emotion recognition with self-supervised models using attentive channel-wise correlations and label smoothing
Sofoklis Kakouros, Themos Stafylakis, Ladislav Mosner +1
When recognizing emotions from speech, we encounter two common problems: how to optimally capture emotion-relevant information from the speech signal and how to best quantify or ca…
Multi-Speaker and Wide-Band Simulated Conversations as Training Data for End-to-End Neural Diarization
Federico Landini, Mireia Diez, Alicia Lozano-Diez +1
End-to-end diarization presents an attractive alternative to standard cascaded diarization systems because a single system can handle all aspects of the task at once. Many flavors…
Extracting speaker and emotion information from self-supervised speech models via channel-wise correlations
Themos Stafylakis, Ladislav Mosner, Sofoklis Kakouros +3
Self-supervised learning of speech representations from large amounts of unlabeled data has enabled state-of-the-art results in several speech processing tasks. Aggregating these s…
An attention-based backend allowing efficient fine-tuning of transformer models for speaker verification
Junyi Peng, Oldrich Plchot, Themos Stafylakis +3
In recent years, self-supervised learning paradigm has received extensive attention due to its great success in various down-stream tasks. However, the fine-tuning strategies for a…
Analyzing speaker verification embedding extractors and back-ends under language and channel mismatch
Anna Silnova, Themos Stafylakis, Ladislav Mosner +6
In this paper, we analyze the behavior and performance of speaker embeddings and the back-end scoring model under domain and language mismatch. We present our findings regarding Re…
DPCCN: Densely-Connected Pyramid Complex Convolutional Network for Robust Speech Separation And Extraction
Jiangyu Han, Yanhua Long, Lukas Burget +1
In recent years, a number of time-domain speech separation methods have been proposed. However, most of them are very sensitive to the environments and wide domain coverage tasks.…
MultiSV: Dataset for Far-Field Multi-Channel Speaker Verification
Ladislav Mošner, Oldřich Plchot, Lukáš Burget +1
Motivated by unconsolidated data situation and the lack of a standard benchmark in the field, we complement our previous efforts and present a comprehensive corpus designed for tra…
Revisiting joint decoding based multi-talker speech recognition with DNN acoustic model
Martin Kocour, Kateřina Žmolíková, Lucas Ondel +5
In typical multi-talker speech recognition systems, a neural network-based acoustic model predicts senone state posteriors for each speaker. These are later used by a single-talker…
EAT: Enhanced ASR-TTS for Self-supervised Speech Recognition
Murali Karthick Baskar, Lukáš Burget, Shinji Watanabe +2
Self-supervised ASR-TTS models suffer in out-of-domain data conditions. Here we propose an enhanced ASR-TTS (EAT) model that incorporates two main features: 1) The ASR…
Speaker embeddings by modeling channel-wise correlations
Themos Stafylakis, Johan Rohdin, Lukas Burget
Speaker embeddings extracted with deep 2D convolutional neural networks are typically modeled as projections of first and second order statistics of channel-frequency pairs onto a…
Bayesian HMM clustering of x-vector sequences (VBx) in speaker diarization: theory, implementation and analysis on standard tasks
Federico Landini, Ján Profant, Mireia Diez +1
The recently proposed VBx diarization method uses a Bayesian hidden Markov model to find speaker clusters in a sequence of x-vectors. In this work we perform an extensive compariso…
Integration of variational autoencoder and spatial clustering for adaptive multi-channel neural speech separation
Katerina Zmolikova, Marc Delcroix, Lukáš Burget +2
In this paper, we propose a method combining variational autoencoder model of speech with a spatial clustering approach for multi-channel speech separation. The advantage of integr…
A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery
Bolaji Yusuf, Lucas Ondel, Lukas Burget +2
In this work, we propose a hierarchical subspace model for acoustic unit discovery. In this approach, we frame the task as one of learning embeddings on a low-dimensional phonetic…
Analysis of the BUT Diarization System for VoxConverse Challenge
Federico Landini, Ondřej Glembek, Pavel Matějka +4
This paper describes the system developed by the BUT team for the fourth track of the VoxCeleb Speaker Recognition Challenge, focusing on diarization on the VoxConverse dataset. Th…
BUT System for the Second DIHARD Speech Diarization Challenge
Federico Landini, Shuai Wang, Mireia Diez +9
This paper describes the winning systems developed by the BUT team for the four tracks of the Second DIHARD Speech Diarization Challenge. For tracks 1 and 2 the systems were mainly…
A Multi Purpose and Large Scale Speech Corpus in Persian and English for Speaker and Speech Recognition: the DeepMine Database
Hossein Zeinali, Lukáš Burget, Jan "Honza'' Černocký
DeepMine is a speech database in Persian and English designed to build and evaluate text-dependent, text-prompted, and text-independent speaker verification, as well as Persian spe…
Short-duration Speaker Verification (SdSV) Challenge 2021: the Challenge Evaluation Plan
Hossein Zeinali, Kong Aik Lee, Jahangir Alam +1
This document describes the Short-duration Speaker Verification (SdSV) Challenge 2021. The main goal of the challenge is to evaluate new technologies for text-dependent (TD) and te…
Acoustic Scene Classification Using Fusion of Attentive Convolutional Neural Networks for DCASE2019 Challenge
Hossein Zeinali, Lukáš Burget, Jan "Honza'' Černocký
In this report, the Brno University of Technology (BUT) team submissions for Task 1 (Acoustic Scene Classification, ASC) of the DCASE-2019 challenge are described. Also, the analys…
BUT VOiCES 2019 System Description
Hossein Zeinali, Pavel Matějka, Ladislav Mošner +6
This is a description of our effort in VOiCES 2019 Speaker Recognition challenge. All systems in the fixed condition are based on the x-vector paradigm with different features and…
Semi-supervised Sequence-to-sequence ASR using Unpaired Speech and Text
Murali Karthick Baskar, Shinji Watanabe, Ramon Astudillo +3
Sequence-to-sequence automatic speech recognition (ASR) models require large quantities of data to attain high performance. For this reason, there has been a recent surge in intere…
Factorization of Discriminatively Trained i-vector Extractor for Speaker Recognition
Ondrej Novotny, Oldrich Plchot, Ondrej Glembek +1
In this work, we continue in our research on i-vector extractor for speaker verification (SV) and we optimize its architecture for fast and effective discriminative training. We we…
Analysis of DNN Speech Signal Enhancement for Robust Speaker Recognition
Ondrej Novotny, Oldrich Plchot, Ondrej Glembek +2
In this work, we present an analysis of a DNN-based autoencoder for speech enhancement, dereverberation and denoising. The target application is a robust speaker verification (SV)…