Search Results for author:
Found 32 papers, 8 papers with code
Temporal Order Preserved Optimal Transport-based Cross-modal Knowledge Transfer Learning for ASR
Transferring linguistic knowledge from a pretrained language model (PLM) to an acoustic model has been shown to greatly improve the performance of automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Robust Channel Learning for Large-Scale Radio Speaker Verification
To address this issue, we present a Channel Robust Speaker Learning (CRSL) framework that enhances the robustness of the current speaker verification pipeline, considering data source, data augmentation, and the efficiency of model transfer processes.
A Non-Intrusive Neural Quality Assessment Model for Surface Electromyography Signals
In practical scenarios involving the measurement of surface electromyography (sEMG) in muscles, particularly those areas near the heart, one of the primary sources of contamination is the presence of electrocardiogram (ECG) signals.
Speaker Mask Transformer for Multi-talker Overlapped Speech Recognition
Multi-talker overlapped speech recognition remains a significant challenge, requiring not only speech recognition but also speaker diarization tasks to be addressed.
Neural domain alignment for spoken language recognition based on optimal transport
Our previous study discovered that completely aligning the distributions between the source and target domains can introduce a negative transfer, where classes or irrelevant classes from the source domain map to a different class in the target domain during distribution alignment.
Hierarchical Cross-Modality Knowledge Transfer with Sinkhorn Attention for CTC-based ASR
Due to the modality discrepancy between textual and acoustic modeling, efficiently transferring linguistic knowledge from a pretrained language model (PLM) to acoustic encoding for automatic speech recognition (ASR) still remains a challenging task.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Cross-modal Alignment with Optimal Transport for CTC-based ASR
Since the PLM is built from text while the acoustic model is trained with speech, a cross-modal alignment is required in order to transfer the context dependent linguistic knowledge from the PLM to acoustic encoding.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Pronunciation-aware unique character encoding for RNN Transducer-based Mandarin speech recognition
For Mandarin end-to-end (E2E) automatic speech recognition (ASR) tasks, compared to character-based modeling units, pronunciation-based modeling units could improve the sharing of modeling units in model training but meet homophone problems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Transducer-based language embedding for spoken language identification
The acoustic and linguistic features are important cues for the spoken language identification (LID) task.
Perceptual Contrast Stretching on Target Feature for Speech Enhancement
Specifically, the contrast of target features is stretched based on perceptual importance, thereby improving the overall SE performance.
Ranked #8 on
Speech Enhancement
on VoiceBank + DEMAND
Partial Coupling of Optimal Transport for Spoken Language Identification
In order to reduce domain discrepancy to improve the performance of cross-domain spoken language identification (SLID) system, as an unsupervised domain adaptation (UDA) method, we have proposed a joint distribution alignment (JDA) model based on optimal transport (OT).
TMS: A Temporal Multi-scale Backbone Design for Speaker Embedding
Therefore, in the most current state-of-the-art network architectures, only a few branches corresponding to a limited number of temporal scales could be designed for speaker embeddings.
A Novel Temporal Attentive-Pooling based Convolutional Recurrent Architecture for Acoustic Signal Enhancement
To address this problem, we propose to integrate a novel temporal attentive-pooling (TAP) mechanism into a conventional convolutional recurrent neural network, termed as TAP-CRNN.
Unsupervised Noise Adaptive Speech Enhancement by Discriminator-Constrained Optimal Transport
This paper presents a novel discriminator-constrained optimal transport network (DOTN) that performs unsupervised domain adaptation for speech enhancement (SE), which is an essential regression task in speech processing.
CS-Rep: Making Speaker Verification Networks Embracing Re-parameterization
Automatic speaker verification (ASV) systems, which determine whether two speeches are from the same speaker, mainly focus on verification accuracy while ignoring inference speed.
MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement
The discrepancy between the cost function used for training a speech enhancement model and human auditory perception usually makes the quality of enhanced speech unsatisfactory.
Ranked #16 on
Speech Enhancement
on VoiceBank + DEMAND
Siamese Neural Network with Joint Bayesian Model Structure for Speaker Verification
However, in most of the discriminative training for SiamNN, only the distribution of pair-wised sample distances is considered, and the additional discriminative information in joint distribution of samples is ignored.
EMA2S: An End-to-End Multimodal Articulatory-to-Speech System
Synthesized speech from articulatory movements can have real-world use for patients with vocal cord disorders, situations requiring silent speech, or in high-noise environments.
Coupling a generative model with a discriminative learning framework for speaker verification
By initializing the two-branch neural network with the generatively learned model parameters of the JB model, we train the model parameters with the pairwise samples as a binary discrimination task.
Unsupervised neural adaptation model based on optimal transport for spoken language identification
By minimizing the classification loss on the training data set with the adaptation loss on both training and testing data sets, the statistical distribution difference between training and testing domains is reduced.
A Study of Incorporating Articulatory Movement Information in Speech Enhancement
Although deep learning algorithms are widely used for improving speech enhancement (SE) performance, the performance remains limited under highly challenging conditions, such as unseen noise or noise signals having low signal-to-noise ratios (SNRs).
Improving Perceptual Quality by Phone-Fortified Perceptual Loss using Wasserstein Distance for Speech Enhancement
Speech enhancement (SE) aims to improve speech quality and intelligibility, which are both related to a smooth transition in speech segments that may carry linguistic information, e. g. phones and syllables.
Ranked #16 on
Speech Enhancement
on VoiceBank + DEMAND
Incorporating Broad Phonetic Information for Speech Enhancement
In noisy conditions, knowing speech contents facilitates listeners to more effectively suppress background noise components and to retrieve pure speech signals.
WaveCRN: An Efficient Convolutional Recurrent Neural Network for End-to-end Speech Enhancement
In WaveCRN, the speech locality feature is captured by a convolutional neural network (CNN), while the temporal sequential property of the locality feature is modeled by stacked simple recurrent units (SRU).
Robust Unsupervised Neural Machine Translation with Adversarial Denoising Training
Unsupervised neural machine translation (UNMT) has recently attracted great interest in the machine translation community.
Speech Enhancement based on Denoising Autoencoder with Multi-branched Encoders
The DSDT is built based on a prior knowledge of speech and noisy conditions (the speaker, environment, and signal factors are considered in this paper), where each component of the multi-branched encoder performs a particular mapping from noisy to clean speech along the branch in the DSDT.
Cross-scale Attention Model for Acoustic Event Classification
However, a potential limitation of the network is that the discriminative features from the bottom layers (which can model the short-range dependency) are smoothed out in the final representation.
Incorporating Symbolic Sequential Modeling for Speech Enhancement
In this study, the symbolic sequences for acoustic signals are obtained as discrete representations with a Vector Quantized Variational Autoencoder algorithm.
End-to-End Waveform Utterance Enhancement for Direct Evaluation Metrics Optimization by Fully Convolutional Neural Networks
For example, in measuring speech intelligibility, most of the evaluation metric is based on a short-time objective intelligibility (STOI) measure, while the frame based minimum mean square error (MMSE) between estimated and clean speech is widely used in optimizing the model.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Complex spectrogram enhancement by convolutional neural network with multi-metrics learning
This paper aims to address two issues existing in the current speech enhancement methods: 1) the difficulty of phase estimations; 2) a single objective function cannot consider multiple metrics simultaneously.
Raw Waveform-based Speech Enhancement by Fully Convolutional Networks
Because the fully connected layers, which are involved in deep neural networks (DNN) and convolutional neural networks (CNN), may not accurately characterize the local information of speech signals, particularly with high frequency components, we employed fully convolutional layers to model the waveform.
