Search Results for author:
Found 47 papers, 11 papers with code
An Explicit Consistency-Preserving Loss Function for Phase Reconstruction and Speech Enhancement
Different from conventional techniques that directly estimate the phase using a deep model, our idea is to exploit ad-hoc constraints to directly generate a consistent pair of magnitude and phase.
Exploring Audio-Visual Information Fusion for Sound Event Localization and Detection In Low-Resource Realistic Scenarios
Evaluation results on the Detection and Classification of Acoustic Scenes and Events (DCASE) 2023 Challenge data set demonstrate significant improvements in SELD performances.
Language-Universal Speech Attributes Modeling for Zero-Shot Multilingual Spoken Keyword Recognition
We propose a novel language-universal approach to end-to-end automatic spoken keyword recognition (SKR) leveraging upon (i) a self-supervised pre-trained model, and (ii) a set of universal speech attributes (manner and place of articulation).
A Study of Dropout-Induced Modality Bias on Robustness to Missing Video Frames for Audio-Visual Speech Recognition
In this paper, we investigate this contrasting phenomenon from the perspective of modality bias and reveal that an excessive modality bias on the audio caused by dropout is the underlying reason.
Bayesian adaptive learning to latent variables via Variational Bayes and Maximum a Posteriori
In this work, we aim to establish a Bayesian adaptive learning framework by focusing on estimating latent variables in deep neural network (DNN) models.
Neural Speaker Diarization Using Memory-Aware Multi-Speaker Embedding with Sequence-to-Sequence Architecture
We propose a novel neural speaker diarization system using memory-aware multi-speaker embedding with sequence-to-sequence architecture (NSD-MS2S), which integrates the strengths of memory-aware multi-speaker embedding (MA-MSE) and sequence-to-sequence (Seq2Seq) architecture, leading to improvement in both efficiency and performance.
Continuous Modeling of the Denoising Process for Speech Enhancement Based on Deep Learning
The starting state is noisy speech and the ending state is clean speech.
Boosting End-to-End Multilingual Phoneme Recognition through Exploiting Universal Speech Attributes Constraints
The proposed joint multilingual model is evaluated through phoneme recognition.
The Multimodal Information Based Speech Processing (MISP) 2023 Challenge: Audio-Visual Target Speaker Extraction
This pioneering effort aims to set the first benchmark for the AVTSE task, offering fresh insights into enhancing the ac-curacy of back-end speech recognition systems through AVTSE in challenging and real acoustic environments.
The USTC-NERCSLIP Systems for the CHiME-7 DASR Challenge
This technical report details our submission system to the CHiME-7 DASR Challenge, which focuses on speaker diarization and speech recognition under complex multi-speaker scenarios.
Improving Audio-Visual Speech Recognition by Lip-Subword Correlation Based Visual Pre-training and Cross-Modal Fusion Encoder
In this paper, we propose two novel techniques to improve audio-visual speech recognition (AVSR) under a pre-training and fine-tuning training framework.
Audio-Visual Speech Recognition
Automatic Speech Recognition
+2
Semi-supervised multi-channel speaker diarization with cross-channel attention
Most neural speaker diarization systems rely on sufficient manual training data labels, which are hard to collect under real-world scenarios.
Variance-Preserving-Based Interpolation Diffusion Models for Speech Enhancement
The goal of this study is to implement diffusion models for speech enhancement (SE).
A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Models
We propose a multi-dimensional structured state space (S4) approach to speech enhancement.
A Quantum Kernel Learning Approach to Acoustic Modeling for Spoken Command Recognition
We propose a quantum kernel learning (QKL) framework to address the inherent data sparsity issues often encountered in training large-scare acoustic models in low-resource scenarios.
Deep Learning Based Audio-Visual Multi-Speaker DOA Estimation Using Permutation-Free Loss Function
In this paper, we propose a deep learning based multi-speaker direction of arrival (DOA) estimation with audio and visual signals by using permutation-free loss function.
An Ensemble Teacher-Student Learning Approach with Poisson Sub-sampling to Differential Privacy Preserving Speech Recognition
We propose an ensemble learning framework with Poisson sub-sampling to effectively train a collection of teacher models to issue some differential privacy (DP) guarantee for training data.
An Experimental Study on Private Aggregation of Teacher Ensemble Learning for End-to-End Speech Recognition
We evaluate three end-to-end deep models, including LAS, hybrid CTC/attention, and RNN transducer, on the open-source LibriSpeech and TIMIT corpora.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
A study on joint modeling and data augmentation of multi-modalities for audio-visual scene classification
In this paper, we propose two techniques, namely joint modeling and data augmentation, to improve system performances for audio-visual scene classification (AVSC).
A Study of Designing Compact Audio-Visual Wake Word Spotting System Based on Iterative Fine-Tuning in Neural Network Pruning
Audio-only-based wake word spotting (WWS) is challenging under noisy conditions due to environmental interference in signal transmission.
The USTC-Ximalaya system for the ICASSP 2022 multi-channel multi-party meeting transcription (M2MeT) challenge
We propose two improvements to target-speaker voice activity detection (TS-VAD), the core component in our proposed speaker diarization system that was submitted to the 2022 Multi-Channel Multi-Party Meeting Transcription (M2MeT) challenge.
A Variational Bayesian Approach to Learning Latent Variables for Acoustic Knowledge Transfer
We propose a variational Bayesian (VB) approach to learning distributions of latent variables in deep neural network (DNN) models for cross-domain knowledge transfer, to address acoustic mismatches between training and testing conditions.
Separation Guided Speaker Diarization in Realistic Mismatched Conditions
We propose a separation guided speaker diarization (SGSD) approach by fully utilizing a complementarity of speech separation and speaker clustering.
A Lottery Ticket Hypothesis Framework for Low-Complexity Device-Robust Neural Acoustic Scene Classification
We propose a novel neural model compression strategy combining data augmentation, knowledge transfer, pruning, and quantization for device-robust acoustic scene classification (ASC).
PATE-AAE: Incorporating Adversarial Autoencoder into Private Aggregation of Teacher Ensembles for Spoken Command Classification
We propose using an adversarial autoencoder (AAE) to replace generative adversarial network (GAN) in the private aggregation of teacher ensembles (PATE), a solution for ensuring differential privacy in speech applications.
Ranked #3 on
Keyword Spotting
on Google Speech Commands
(10-keyword Speech Commands dataset metric)
USTC-NELSLIP System Description for DIHARD-III Challenge
This system description describes our submission system to the Third DIHARD Speech Diarization Challenge.
Lip-reading with Hierarchical Pyramidal Convolution and Self-Attention
In this paper, we propose a novel deep learning architecture to improving word-level lip-reading.
A Two-Stage Approach to Device-Robust Acoustic Scene Classification
To improve device robustness, a highly desirable key feature of a competitive data-driven acoustic scene classification (ASC) system, a novel two-stage system based on fully convolutional neural networks (CNNs) is proposed.
Ranked #1 on
Acoustic Scene Classification
on TAU Urban Acoustic Scenes 2019
(using extra training data)
Decentralizing Feature Extraction with Quantum Convolutional Neural Network for Automatic Speech Recognition
Testing on the Google Speech Commands Dataset, the proposed QCNN encoder attains a competitive accuracy of 95. 12% in a decentralized model, which is better than the previous architectures using centralized RNN models with convolutional features.
Ranked #1 on
Keyword Spotting
on Google Speech Commands
(10-keyword Speech Commands dataset metric)
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
A Noise-Aware Memory-Attention Network Architecture for Regression-Based Speech Enhancement
We propose a novel noise-aware memory-attention network (NAMAN) for regression-based speech enhancement, aiming at improving quality of enhanced speech in unseen noise conditions.
Correlating Subword Articulation with Lip Shapes for Embedding Aware Audio-Visual Speech Enhancement
We first extract visual embedding from lip frames using a pre-trained phone or articulation place recognizer for visual-only EASE (VEASE).
On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regression
In this paper, we exploit the properties of mean absolute error (MAE) as a loss function for the deep neural network (DNN) based vector-to-vector regression.
Analyzing Upper Bounds on Mean Absolute Errors for Deep Neural Network Based Vector-to-Vector Regression
In this paper, we show that, in vector-to-vector regression utilizing deep neural networks (DNNs), a generalized loss of mean absolute error (MAE) between the predicted and expected feature vectors is upper bounded by the sum of an approximation error, an estimation error, and an optimization error.
Relational Teacher Student Learning with Neural Label Embedding for Device Adaptation in Acoustic Scene Classification
In this paper, we propose a domain adaptation framework to address the device mismatch issue in acoustic scene classification leveraging upon neural label embedding (NLE) and relational teacher student learning (RTSL).
An Acoustic Segment Model Based Segment Unit Selection Approach to Acoustic Scene Classification with Partial Utterances
In contrast to building scene models with whole utterances, the ASM-removed sub-utterances, i. e., acoustic utterances without stop acoustic segments, are then used as inputs to the AlexNet-L back-end for final classification.
Exploring Deep Hybrid Tensor-to-Vector Network Architectures for Regression Based Speech Enhancement
Finally, our experiments of multi-channel speech enhancement on a simulated noisy WSJ0 corpus demonstrate that our proposed hybrid CNN-TT architecture achieves better results than both DNN and CNN models in terms of better-enhanced speech qualities and smaller parameter sizes.
Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentation
On Task 1b development data set, we achieve an accuracy of 96. 7\% with a model size smaller than 500KB.
L-Vector: Neural Label Embedding for Domain Adaptation
We propose a novel neural label embedding (NLE) scheme for the domain adaptation of a deep neural network (DNN) acoustic model with unpaired data samples from source and target domains.
Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement
Recent studies have highlighted adversarial examples as ubiquitous threats to the deep neural network (DNN) based speech recognition systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Enhanced Adversarial Strategically-Timed Attacks against Deep Reinforcement Learning
Recent deep neural networks based techniques, especially those equipped with the ability of self-adaptation in the system level such as deep reinforcement learning (DRL), are shown to possess many advantages of optimizing robot learning systems (e. g., autonomous navigation and continuous robot arm control.)
Tensor-to-Vector Regression for Multi-channel Speech Enhancement based on Tensor-Train Network
Finally, in 8-channel conditions, a PESQ of 3. 12 is achieved using 20 million parameters for TTN, whereas a DNN with 68 million parameters can only attain a PESQ of 3. 06.
Riemannian Stochastic Gradient Descent for Tensor-Train Recurrent Neural Networks
The Tensor-Train factorization (TTF) is an efficient way to compress large weight matrices of fully-connected layers and recurrent layers in recurrent neural networks (RNNs).
Convolutional-Recurrent Neural Networks for Speech Enhancement
By incorporating prior knowledge of speech signals into the design of model structures, we build a model that is more data-efficient and achieves better generalization on both seen and unseen noise.
Multi-Objective Learning and Mask-Based Post-Processing for Deep Neural Network Based Speech Enhancement
We propose a multi-objective framework to learn both secondary targets not directly related to the intended task of speech enhancement (SE) and the primary target of the clean log-power spectra (LPS) features to be used directly for constructing the enhanced speech signals.
Sound
A Probabilistic Framework for Representing Dialog Systems and Entropy-Based Dialog Management through Dynamic Stochastic State Evolution
A Song-On-Demand task, with a total of 38117 songs and 12 attributes corresponding to each song, is used to test the performance of the proposed approach.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Maximum a Posteriori Adaptation of Network Parameters in Deep Models
We present a Bayesian approach to adapting parameters of a well-trained context-dependent, deep-neural-network, hidden Markov model (CD-DNN-HMM) to improve automatic speech recognition performance.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
