Search Results for author:
Found 53 papers, 13 papers with code
Detecting Post-Stroke Aphasia Via Brain Responses to Speech in a Deep Learning Framework
We modeled electroencephalography (EEG) responses to acoustic, segmentation, and linguistic speech representations of a story using convolutional neural networks trained on a large sample of healthy participants, serving as a model for intact neural tracking of speech.
Unsupervised Accent Adaptation Through Masked Language Model Correction Of Discrete Self-Supervised Speech Units
Self-supervised pre-trained speech models have strongly improved speech recognition, yet they are still sensitive to domain shifts and accented or atypical speech.
Analysis of XLS-R for Speech Quality Assessment
In online conferencing applications, estimating the perceived quality of an audio signal is crucial to ensure high quality of experience for the end user.
The role of vowel and consonant onsets in neural tracking of natural speech
Our results show that vowel-consonant onsets outperform onsets of any phone in both tasks, which suggests that neural tracking of the vowel vs. consonant exists in the EEG to some degree.
Rehearsal-Free Online Continual Learning for Automatic Speech Recognition
Fine-tuning an Automatic Speech Recognition (ASR) model to new domains results in degradation on original domains, referred to as Catastrophic Forgetting (CF).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Parameter-efficient Dysarthric Speech Recognition Using Adapter Fusion and Householder Transformation
In dysarthric speech recognition, data scarcity and the vast diversity between dysarthric speakers pose significant challenges.
Cross-Lingual Transfer Learning for Alzheimer's Detection From Spontaneous Speech
To fill this gap, the ADReSS-M challenge was organized.
Relating EEG to continuous speech using deep neural networks: a review
Linear models are presently used to relate the EEG recording to the corresponding speech signal.
Self-supervised enhancement of stimulus-evoked brain response data
We propose a novel paradigm for the self-supervised enhancement of stimulus-related brain response data.
Bidirectional Representations for Low Resource Spoken Language Understanding
Class attention can be used to visually explain the predictions of our model, which goes a long way in understanding how the model makes predictions.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Multitask Learning for Low Resource Spoken Language Understanding
We explore the benefits that multitask learning offer to speech processing as we train models on dual objectives with automatic speech recognition and intent classification or sentiment classification.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+7
Impact of visual assistance for automated audio captioning
More specifically, visual features focusing on semantics appear appropriate in the context of automated audio captioning, while for sound event detection, time information seems to be more important.
Weight Averaging: A Simple Yet Effective Method to Overcome Catastrophic Forgetting in Automatic Speech Recognition
Adapting a trained Automatic Speech Recognition (ASR) model to new tasks results in catastrophic forgetting of old tasks, limiting the model's ability to learn continually and to be extended to new speakers, dialects, languages, etc.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Weak-Supervised Dysarthria-invariant Features for Spoken Language Understanding using an FHVAE and Adversarial Training
The scarcity of training data and the large speaker variation in dysarthric speech lead to poor accuracy and poor speaker generalization of spoken language understanding systems for dysarthric speech.
Multi-Source Transformer Architectures for Audiovisual Scene Classification
With regard to the accuracy measure, our best model achieved a score of 77. 1\% on the validation data, which is about the same as the performance obtained by the baseline system (77. 0\%).
Optimizing Temporal Resolution Of Convolutional Recurrent Neural Networks For Sound Event Detection
This is significantly better than the performance obtained by the baseline model (0. 527), which can effectively be attributed to the changes that were applied to the pooling operations of the network.
Learning to Jointly Transcribe and Subtitle for End-to-End Spontaneous Speech Recognition
However, subtitles are not verbatim (i. e. exact) transcriptions of speech, so they cannot be used directly to improve an Automatic Speech Recognition (ASR) model.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Pre-trained Speech Representations as Feature Extractors for Speech Quality Assessment in Online Conferencing Applications
Speech quality in online conferencing applications is typically assessed through human judgements in the form of the mean opinion score (MOS) metric.
Impact of temporal resolution on convolutional recurrent networks for audio tagging and sound event detection
Many state-of-the-art systems for audio tagging and sound event detection employ convolutional recurrent neural architectures.
Multi-encoder attention-based architectures for sound recognition with partial visual assistance
Large-scale sound recognition data sets typically consist of acoustic recordings obtained from multimedia libraries.
Relating the fundamental frequency of speech with EEG using a dilated convolutional network
To investigate how speech is processed in the brain, we can model the relation between features of a natural speech signal and the corresponding recorded electroencephalogram (EEG).
Learning Subject-Invariant Representations from Speech-Evoked EEG Using Variational Autoencoders
The electroencephalogram (EEG) is a powerful method to understand how the brain processes speech.
Bottleneck Low-rank Transformers for Low-resource Spoken Language Understanding
End-to-end spoken language understanding (SLU) systems benefit from pretraining on large corpora, followed by fine-tuning on application-specific data.
Using Adapters to Overcome Catastrophic Forgetting in End-to-End Automatic Speech Recognition
In this paper, we aim to overcome CF for E2E ASR by inserting adapters, small architectures of few parameters which allow a general model to be fine-tuned to a specific task, into our model.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Continual Learning for Monolingual End-to-End Automatic Speech Recognition
Adapting Automatic Speech Recognition (ASR) models to new domains results in a deterioration of performance on the original domain(s), a phenomenon called Catastrophic Forgetting (CF).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Comparison of Self-Supervised Speech Pre-Training Methods on Flemish Dutch
Recent research in speech processing exhibits a growing interest in unsupervised and self-supervised representation learning from unlabelled data to alleviate the need for large amounts of annotated data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Extracting Different Levels of Speech Information from EEG Using an LSTM-Based Model
Decoding the speech signal that a person is listening to from the human brain via electroencephalography (EEG) can help us understand how our auditory system works.
On the long-term learning ability of LSTM LMs
We inspect the long-term learning ability of Long Short-Term Memory language models (LSTM LMs) by evaluating a contextual extension based on the Continuous Bag-of-Words (CBOW) model for both sentence- and discourse-level LSTM LMs and by analyzing its performance.
A Study into Pre-training Strategies for Spoken Language Understanding on Dysarthric Speech
The acoustic model is pre-trained in two stages: initialization with a corpus of normal speech and finetuning on a mixture of dysarthric and normal speech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Speech Disorder Classification Using Extended Factorized Hierarchical Variational Auto-encoders
We show that an extension of the FHVAE model succeeds in the better disentanglement of the content-related and sequence-related related representations, but both representations are still required for best results on disorder type classification.
Audiovisual transfer learning for audio tagging and sound event detection
We study the merit of transfer learning for two sound recognition problems, i. e., audio tagging and sound event detection.
Predicting speech intelligibility from EEG in a non-linear classification paradigm
The accuracy of the model's match/mismatch predictions can be used as a proxy for speech intelligibility without subject-specific (re)training.
Pre-training for low resource speech-to-intent applications
In this paper we combine the encoder of an end-to-end ASR system with the prior NMF/capsule network-based user-taught decoder, and investigate whether pre-training methodology can reduce training data requirements for the NMF and capsule network.
CNN-LSTM models for Multi-Speaker Source Separation using Bayesian Hyper Parameter Optimization
In this paper we propose a novel network for source separation using an encoder-decoder CNN and LSTM in parallel.
Practical applicability of deep neural networks for overlapping speaker separation
This paper examines the applicability in realistic scenarios of two deep learning based solutions to the overlapping speaker separation problem.
Audiovisual Transformer Architectures for Large-Scale Classification and Synchronization of Weakly Labeled Audio Events
We tackle the task of environmental event classification by drawing inspiration from the transformer neural network architecture used in machine translation.
Effective weakly supervised semantic frame induction using expression sharing in hierarchical hidden Markov models
We present a framework for the induction of semantic frames from utterances in the context of an adaptive command-and-control interface.
Information-Weighted Neural Cache Language Models for ASR
Neural cache language models (LMs) extend the idea of regular cache language models by making the cache probability dependent on the similarity between the current context and the context of the words in the cache.
Memory Time Span in LSTMs for Multi-Speaker Source Separation
With deep learning approaches becoming state-of-the-art in many speech (as well as non-speech) related machine learning tasks, efforts are being taken to delve into the neural networks which are often considered as a black box.
Multi-scenario deep learning for multi-speaker source separation
Furthermore, it is concluded that a single model, trained on different scenarios is capable of matching performance of scenario specific models.
State Gradients for RNN Memory Analysis
We present a framework for analyzing what the state in RNNs remembers from its input embeddings.
Language Models of Spoken Dutch
One model is trained on all available data (46M word tokens), but we also trained models on a specific type of TV show or domain/topic.
Character-Word LSTM Language Models
We present a Character-Word Long Short-Term Memory Language Model which both reduces the perplexity with respect to a baseline word-level language model and reduces the number of parameters of the model.
SCALE: A Scalable Language Engineering Toolkit
In this paper we present SCALE, a new Python toolkit that contains two extensions to n-gram language models.
Joint Sound Source Separation and Speaker Recognition
It is shown how state-of-the-art multichannel NMF for blind source separation can be easily extended to incorporate speaker recognition.
Speech Recognition Web Services for Dutch
In this paper we present 3 applications in the domain of Automatic Speech Recognition for Dutch, all of which are developed using our in-house speech recognition toolkit SPRAAK.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
