Search Results for author:
Found 22 papers, 6 papers with code
Leveraging Self-Supervised Learning for Speaker Diarization
In this work, we explore using WavLM to alleviate the problem of data scarcity for neural diarization training.
Challenging margin-based speaker embedding extractors by using the variational information bottleneck
Speaker embedding extractors are typically trained using a classification loss over the training speakers.
DiaCorrect: Error Correction Back-end For Speaker Diarization
In this work, we propose an error correction framework, named DiaCorrect, to refine the output of a diarization system in a simple yet effective way.
Multi-Stream Extension of Variational Bayesian HMM Clustering (MS-VBx) for Combined End-to-End and Vector Clustering-based Diarization
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.
Stabilized training of joint energy-based models and their practical applications
The JEM training relies on "positive examples" (i. e. examples from the training data set) as well as on "negative examples", which are samples from the modeled distribution $p(x)$ generated by means of Stochastic Gradient Langevin Dynamics (SGLD).
Speech-based emotion recognition with self-supervised models using attentive channel-wise correlations and label smoothing
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 categorize the noisy subjective emotion labels.
Extracting speaker and emotion information from self-supervised speech models via channel-wise correlations
Self-supervised learning of speech representations from large amounts of unlabeled data has enabled state-of-the-art results in several speech processing tasks.
An attention-based backend allowing efficient fine-tuning of transformer models for speaker verification
In recent years, self-supervised learning paradigm has received extensive attention due to its great success in various down-stream tasks.
Analyzing speaker verification embedding extractors and back-ends under language and channel mismatch
In this paper, we analyze the behavior and performance of speaker embeddings and the back-end scoring model under domain and language mismatch.
DPCCN: Densely-Connected Pyramid Complex Convolutional Network for Robust Speech Separation And Extraction
Particularly, we find that the Mixture-Remix fine-tuning with DPCCN significantly outperforms the TD-SpeakerBeam for unsupervised cross-domain TSE, with around 3. 5 dB SISNR improvement on target domain test set, without any source domain performance degradation.
Speaker embeddings by modeling channel-wise correlations
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 linear layer, using either average or attentive pooling along the time axis.
A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery
In the target language, we infer both the language and unit embeddings in an unsupervised manner, and in so doing, we simultaneously learn a subspace of units specific to that language and the units that dwell on it.
A Technical Report: BUT Speech Translation Systems
To reduce this performance degradation, we have jointly-trained ASR and MT modules with ASR objective as an auxiliary loss.
Short-duration Speaker Verification (SdSV) Challenge 2021: the Challenge Evaluation Plan
This document describes the Short-duration Speaker Verification (SdSV) Challenge 2021.
Self-supervised speaker embeddings
Contrary to i-vectors, speaker embeddings such as x-vectors are incapable of leveraging unlabelled utterances, due to the classification loss over training speakers.
How to Improve Your Speaker Embeddings Extractor in Generic Toolkits
Recently, speaker embeddings extracted with deep neural networks became the state-of-the-art method for speaker verification.
Spoken Pass-Phrase Verification in the i-vector Space
The task of spoken pass-phrase verification is to decide whether a test utterance contains the same phrase as given enrollment utterances.
Residual Memory Networks: Feed-forward approach to learn long temporal dependencies
In this paper we propose a residual memory neural network (RMN) architecture to model short-time dependencies using deep feed-forward layers having residual and time delayed connections.
Fast variational Bayes for heavy-tailed PLDA applied to i-vectors and x-vectors
We have recently introduced a fast scoring algorithm for a discriminatively trained HT-PLDA backend.
Gaussian meta-embeddings for efficient scoring of a heavy-tailed PLDA model
Embeddings in machine learning are low-dimensional representations of complex input patterns, with the property that simple geometric operations like Euclidean distances and dot products can be used for classification and comparison tasks.
Bayesian Models for Unit Discovery on a Very Low Resource Language
Developing speech technologies for low-resource languages has become a very active research field over the last decade.
An Empirical Evaluation of Zero Resource Acoustic Unit Discovery
Acoustic unit discovery (AUD) is a process of automatically identifying a categorical acoustic unit inventory from speech and producing corresponding acoustic unit tokenizations.
