Search Results for author:
Found 33 papers, 17 papers with code
CA-MHFA: A Context-Aware Multi-Head Factorized Attentive Pooling for SSL-Based Speaker Verification
Self-supervised learning (SSL) models for speaker verification (SV) have gained significant attention in recent years.
Target Speaker ASR with Whisper
We propose a novel approach to enable the use of large, single speaker ASR models, such as Whisper, for target speaker ASR.
Beyond the Labels: Unveiling Text-Dependency in Paralinguistic Speech Recognition Datasets
This paper critically evaluates the prevalent assumption that machine learning models trained on such datasets genuinely learn to identify paralinguistic traits, rather than merely capturing lexical features.
DiaPer: End-to-End Neural Diarization with Perceiver-Based Attractors
Until recently, the field of speaker diarization was dominated by cascaded systems.
Discriminative Training of VBx Diarization
Bayesian HMM clustering of x-vector sequences (VBx) has become a widely adopted diarization baseline model in publications and challenges.
Hystoc: Obtaining word confidences for fusion of end-to-end ASR systems
Furthermore, we show that utilizing Hystoc in fusion of multiple e2e ASR systems increases the gains from the fusion by up to 1\,\% WER absolute on Spanish RTVE2020 dataset.
Improving Speaker Verification with Self-Pretrained Transformer Models
Recently, fine-tuning large pre-trained Transformer models using downstream datasets has received a rising interest.
Multi-Speaker and Wide-Band Simulated Conversations as Training Data for End-to-End Neural Diarization
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.
Parameter-efficient transfer learning of pre-trained Transformer models for speaker verification using adapters
Recently, the pre-trained Transformer models have received a rising interest in the field of speech processing thanks to their great success in various downstream tasks.
Toroidal Probabilistic Spherical Discriminant Analysis
It extends PSDA with the ability to model within and between-speaker variabilities in toroidal submanifolds of the hypersphere.
Speaker adaptation for Wav2vec2 based dysarthric ASR
Speaker adaptation using fMLLR and xvectors have provided major gains for dysarthric speech with very little adaptation data.
From Simulated Mixtures to Simulated Conversations as Training Data for End-to-End Neural Diarization
However, simulated mixtures do not resemble real conversations in many aspects.
Training Speaker Embedding Extractors Using Multi-Speaker Audio with Unknown Speaker Boundaries
In this paper, we demonstrate a method for training speaker embedding extractors using weak annotation.
Probabilistic Spherical Discriminant Analysis: An Alternative to PLDA for length-normalized embeddings
In speaker recognition, where speech segments are mapped to embeddings on the unit hypersphere, two scoring backends are commonly used, namely cosine scoring or PLDA.
MultiSV: Dataset for Far-Field Multi-Channel Speaker Verification
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 training and evaluating text-independent multi-channel speaker verification systems.
Revisiting joint decoding based multi-talker speech recognition with DNN acoustic model
We modify the acoustic model to predict joint state posteriors for all speakers, enabling the network to express uncertainty about the attribution of parts of the speech signal to the speakers.
GPU-Accelerated Forward-Backward algorithm with Application to Lattice-Free MMI
We propose to express the forward-backward algorithm in terms of operations between sparse matrices in a specific semiring.
EAT: Enhanced ASR-TTS for Self-supervised Speech Recognition
Self-supervised ASR-TTS models suffer in out-of-domain data conditions.
Integration of variational autoencoder and spatial clustering for adaptive multi-channel neural speech separation
In this paper, we propose a method combining variational autoencoder model of speech with a spatial clustering approach for multi-channel speech separation.
Audio and Speech Processing
Text Augmentation for Language Models in High Error Recognition Scenario
We examine the effect of data augmentation for training of language models for speech recognition.
A Bayesian Multilingual Document Model for Zero-shot Topic Identification and Discovery
In this paper, we present a Bayesian multilingual document model for learning language-independent document embeddings.
Multiwavelength classification of X-ray selected galaxy cluster candidates using convolutional neural networks
The results of using CNNs on combined X-ray and optical data for galaxy cluster candidate classification are encouraging and there is a lot of potential for future usage and improvements.
Cosmology and Nongalactic Astrophysics High Energy Astrophysical Phenomena Instrumentation and Methods for Astrophysics
Probabilistic embeddings for speaker diarization
We apply the proposed probabilistic embeddings as input to an agglomerative hierarchical clustering (AHC) algorithm to do diarization in the DIHARD'19 evaluation set.
A Multi Purpose and Large Scale Speech Corpus in Persian and English for Speaker and Speech Recognition: the DeepMine Database
We also provide the results of several experiments that can be considered as baselines: HMM-based i-vectors for text-dependent speaker verification, and HMM-based as well as state-of-the-art deep neural network based ASR.
BUT System Description for DIHARD Speech Diarization Challenge 2019
This paper describes the systems developed by the BUT team for the four tracks of the second DIHARD speech diarization challenge.
Learning document embeddings along with their uncertainties
We present Bayesian subspace multinomial model (Bayesian SMM), a generative log-linear model that learns to represent documents in the form of Gaussian distributions, thereby encoding the uncertainty in its co-variance.
Ranked #1 on
Topic Models
on 20 Newsgroups
Detecting Spoofing Attacks Using VGG and SincNet: BUT-Omilia Submission to ASVspoof 2019 Challenge
In this paper, we present the system description of the joint efforts of Brno University of Technology (BUT) and Omilia -- Conversational Intelligence for the ASVSpoof2019 Spoofing and Countermeasures Challenge.
BUT VOiCES 2019 System Description
This is a description of our effort in VOiCES 2019 Speaker Recognition challenge.
Semi-supervised Sequence-to-sequence ASR using Unpaired Speech and Text
Such techniques derive training procedures and losses able to leverage unpaired speech and/or text data by combining ASR with Text-to-Speech (TTS) models.
Ranked #34 on
Semi-Supervised Image Classification
on ImageNet - 10% labeled data
(Top 5 Accuracy metric)
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Bayesian Subspace Hidden Markov Model for Acoustic Unit Discovery
This work tackles the problem of learning a set of language specific acoustic units from unlabeled speech recordings given a set of labeled recordings from other languages.
BUT-FIT at SemEval-2019 Task 7: Determining the Rumour Stance with Pre-Trained Deep Bidirectional Transformers
This paper describes our system submitted to SemEval 2019 Task 7: RumourEval 2019: Determining Rumour Veracity and Support for Rumours, Subtask A (Gorrell et al., 2019).
Promising Accurate Prefix Boosting for sequence-to-sequence ASR
In this paper, we present promising accurate prefix boosting (PAPB), a discriminative training technique for attention based sequence-to-sequence (seq2seq) ASR.
BUT QUESST 2014 System Description
The primary system we submitted was composed of 11 subsystems as the required run.
Ranked #1 on
Keyword Spotting
on QUESST
(MinCnxe metric)
