Search Results for author:
Found 26 papers, 9 papers with code
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.
Comparing Data Augmentation Methods for End-to-End Task-Oriented Dialog Systems
Data augmentation (DA), whereby synthetic training examples are added to the training data, has been successful in other NLP systems, but has not been explored as extensively in ToDSs.
DiaPer: End-to-End Neural Diarization with Perceiver-Based Attractors
Until recently, the field of speaker diarization was dominated by cascaded systems.
A Simple Baseline for Knowledge-Based Visual Question Answering
This paper is on the problem of Knowledge-Based Visual Question Answering (KB-VQA).
Ranked #5 on
Visual Question Answering (VQA)
on A-OKVQA
(DA VQA Score metric)
Improving Speaker Verification with Self-Pretrained Transformer Models
Recently, fine-tuning large pre-trained Transformer models using downstream datasets has received a rising interest.
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.
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.
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.
On the Use of Semantically-Aligned Speech Representations for Spoken Language Understanding
In this paper we examine the use of semantically-aligned speech representations for end-to-end spoken language understanding (SLU).
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.
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.
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.
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.
Seeing wake words: Audio-visual Keyword Spotting
The goal of this work is to automatically determine whether and when a word of interest is spoken by a talking face, with or without the audio.
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.
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.
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.
Pushing the boundaries of audiovisual word recognition using Residual Networks and LSTMs
A further analysis on the utility of target word boundaries is provided, as well as on the capacity of the network in modeling the linguistic context of the target word.
Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture
Therefore, we could use a CTC loss in combination with an attention-based model in order to force monotonic alignments and at the same time get rid of the conditional independence assumption.
Ranked #5 on
Audio-Visual Speech Recognition
on LRS2
Audio-Visual Speech Recognition
Automatic Speech Recognition (ASR)
+3
Zero-shot keyword spotting for visual speech recognition in-the-wild
Visual keyword spotting (KWS) is the problem of estimating whether a text query occurs in a given recording using only video information.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
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.
End-to-end Audiovisual Speech Recognition
In presence of high levels of noise, the end-to-end audiovisual model significantly outperforms both audio-only models.
Ranked #20 on
Lipreading
on Lip Reading in the Wild
Deep word embeddings for visual speech recognition
In this paper we present a deep learning architecture for extracting word embeddings for visual speech recognition.
Combining Residual Networks with LSTMs for Lipreading
We propose an end-to-end deep learning architecture for word-level visual speech recognition.
Ranked #22 on
Lipreading
on Lip Reading in the Wild
