Search Results for author:
Found 38 papers, 8 papers with code
Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognition
Despite the rapid progress of automatic speech recognition (ASR) technologies targeting normal speech, accurate recognition of dysarthric and elderly speech remains highly challenging tasks to date.
Audio-visual multi-channel speech separation, dereverberation and recognition
Despite the rapid advance of automatic speech recognition (ASR) technologies, accurate recognition of cocktail party speech characterised by the interference from overlapping speakers, background noise and room reverberation remains a highly challenging task to date.
Neural Architecture Search for Speech Emotion Recognition
Deep neural networks have brought significant advancements to speech emotion recognition (SER).
On-the-fly Feature Based Speaker Adaptation for Dysarthric and Elderly Speech Recognition
Automatic recognition of dysarthric and elderly speech highly challenging tasks to date.
Exploiting Cross Domain Acoustic-to-articulatory Inverted Features For Disordered Speech Recognition
Articulatory features are inherently invariant to acoustic signal distortion and have been successfully incorporated into automatic speech recognition (ASR) systems for normal speech.
Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition
Motivated by the spectro-temporal level differences between dysarthric, elderly and normal speech that systematically manifest in articulatory imprecision, decreased volume and clarity, slower speaking rates and increased dysfluencies, novel spectrotemporal subspace basis deep embedding features derived using SVD speech spectrum decomposition are proposed in this paper to facilitate auxiliary feature based speaker adaptation of state-of-the-art hybrid DNN/TDNN and end-to-end Conformer speech recognition systems.
Speaker Identity Preservation in Dysarthric Speech Reconstruction by Adversarial Speaker Adaptation
The primary task of ASA fine-tunes the SE with the speech of the target dysarthric speaker to effectively capture identity-related information, and the secondary task applies adversarial training to avoid the incorporation of abnormal speaking patterns into the reconstructed speech, by regularizing the distribution of reconstructed speech to be close to that of reference speech with high quality.
VCVTS: Multi-speaker Video-to-Speech synthesis via cross-modal knowledge transfer from voice conversion
Though significant progress has been made for speaker-dependent Video-to-Speech (VTS) synthesis, little attention is devoted to multi-speaker VTS that can map silent video to speech, while allowing flexible control of speaker identity, all in a single system.
Investigation of Deep Neural Network Acoustic Modelling Approaches for Low Resource Accented Mandarin Speech Recognition
Meanwhile, approaches of multi-accent modelling including multi-style training, multi-accent decision tree state tying, DNN tandem and multi-level adaptive network (MLAN) tandem hidden Markov model (HMM) modelling are combined and compared in this paper.
Variational Auto-Encoder Based Variability Encoding for Dysarthric Speech Recognition
Dysarthric speech recognition is a challenging task due to acoustic variability and limited amount of available data.
Recent Progress in the CUHK Dysarthric Speech Recognition System
Despite the rapid progress of automatic speech recognition (ASR) technologies in the past few decades, recognition of disordered speech remains a highly challenging task to date.
Audio-Visual Speech Recognition
Automatic Speech Recognition
+2
Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognition
Automatic recognition of disordered speech remains a highly challenging task to date.
Investigation of Data Augmentation Techniques for Disordered Speech Recognition
This paper investigates a set of data augmentation techniques for disordered speech recognition, including vocal tract length perturbation (VTLP), tempo perturbation and speed perturbation.
Neural Architecture Search For LF-MMI Trained Time Delay Neural Networks
State-of-the-art automatic speech recognition (ASR) system development is data and computation intensive.
Mixed Precision of Quantization of Transformer Language Models for Speech Recognition
Experiments conducted on Penn Treebank (PTB) and a Switchboard corpus trained LF-MMI TDNN system suggest the proposed mixed precision Transformer quantization techniques achieved model size compression ratios of up to 16 times over the full precision baseline with no recognition performance degradation.
Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition
In order to overcome the difficulty in using gradient descent methods to directly estimate discrete quantized weights, alternating direction methods of multipliers (ADMM) are used to efficiently train quantized LMs.
Low-bit Quantization of Recurrent Neural Network Language Models Using Alternating Direction Methods of Multipliers
Index Terms: Language models, Recurrent neural networks, Quantization, Alternating direction methods of multipliers.
Adversarial Data Augmentation for Disordered Speech Recognition
Automatic recognition of disordered speech remains a highly challenging task to date.
Channel-wise Gated Res2Net: Towards Robust Detection of Synthetic Speech Attacks
This argument motivates the current work that presents a novel, channel-wise gated Res2Net (CG-Res2Net), which modifies Res2Net to enable a channel-wise gating mechanism in the connection between feature groups.
Unsupervised Domain Adaptation for Dysarthric Speech Detection via Domain Adversarial Training and Mutual Information Minimization
Such systems are particularly susceptible to domain mismatch where the training and testing data come from the source and target domains respectively, but the two domains may differ in terms of speech stimuli, disease etiology, etc.
VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion
One-shot voice conversion (VC), which performs conversion across arbitrary speakers with only a single target-speaker utterance for reference, can be effectively achieved by speech representation disentanglement.
Bayesian Transformer Language Models for Speech Recognition
Performance improvements were also obtained on a cross domain LM adaptation task requiring porting a Transformer LM trained on the Switchboard and Fisher data to a low-resource DementiaBank elderly speech corpus.
Bayesian Learning for Deep Neural Network Adaptation
A key task for speech recognition systems is to reduce the mismatch between training and evaluation data that is often attributable to speaker differences.
Bayesian Learning of LF-MMI Trained Time Delay Neural Networks for Speech Recognition
On a third cross domain adaptation task requiring rapidly porting a 1000 hour LibriSpeech data trained system to a small DementiaBank elderly speech corpus, the proposed Bayesian TDNN LF-MMI systems outperformed the baseline system using direct weight fine-tuning by up to 2. 5\% absolute WER reduction.
Audio-visual Multi-channel Integration and Recognition of Overlapped Speech
Automatic speech recognition (ASR) technologies have been significantly advanced in the past few decades.
Learning Explicit Prosody Models and Deep Speaker Embeddings for Atypical Voice Conversion
Third, a conversion model takes phoneme embeddings and typical prosody features as inputs to generate the converted speech, conditioned on the target DSE that is learned via speaker encoder or speaker adaptation.
Replay and Synthetic Speech Detection with Res2net Architecture
This multiple scaling mechanism significantly improves the countermeasure's generalizability to unseen spoofing attacks.
Any-to-Many Voice Conversion with Location-Relative Sequence-to-Sequence Modeling
During the training stage, an encoder-decoder-based hybrid connectionist-temporal-classification-attention (CTC-attention) phoneme recognizer is trained, whose encoder has a bottle-neck layer.
Understanding the wiring evolution in differentiable neural architecture search
To this end, we pose questions that future differentiable methods for neural wiring discovery need to confront, hoping to evoke a discussion and rethinking on how much bias has been enforced implicitly in existing NAS methods.
Neural Architecture Search For LF-MMI Trained Time Delay Neural Networks
Deep neural networks (DNNs) based automatic speech recognition (ASR) systems are often designed using expert knowledge and empirical evaluation.
Investigating Robustness of Adversarial Samples Detection for Automatic Speaker Verification
Orthogonal to prior approaches, this work proposes to defend ASV systems against adversarial attacks with a separate detection network, rather than augmenting adversarial data into ASV training.
Audio-visual Multi-channel Recognition of Overlapped Speech
Automatic speech recognition (ASR) of overlapped speech remains a highly challenging task to date.
Bayesian x-vector: Bayesian Neural Network based x-vector System for Speaker Verification
Our experiment results indicate that the DNN x-vector system could benefit from BNNs especially when the mismatch problem is severe for evaluations using out-of-domain data.
DSNAS: Direct Neural Architecture Search without Parameter Retraining
We argue that given a computer vision task for which a NAS method is expected, this definition can reduce the vaguely-defined NAS evaluation to i) accuracy of this task and ii) the total computation consumed to finally obtain a model with satisfying accuracy.
Deep segmental phonetic posterior-grams based discovery of non-categories in L2 English speech
And then we explore the non-categories by looking for the SPPGs with more than one peak.
Audio-visual Recognition of Overlapped speech for the LRS2 dataset
Experiments on overlapped speech simulated from the LRS2 dataset suggest the proposed AVSR system outperformed the audio only baseline LF-MMI DNN system by up to 29. 98\% absolute in word error rate (WER) reduction, and produced recognition performance comparable to a more complex pipelined system.
Ranked #7 on
Lipreading
on LRS2
(using extra training data)
Adversarial Attacks on GMM i-vector based Speaker Verification Systems
Experiment results show that GMM i-vector systems are seriously vulnerable to adversarial attacks, and the crafted adversarial samples prove to be transferable and pose threats to neuralnetwork speaker embedding based systems (e. g. x-vector systems).
Future Word Contexts in Neural Network Language Models
Instead of using a recurrent unit to capture the complete future word contexts, a feedforward unit is used to model a finite number of succeeding, future, words.
