arXiv subjects

Wenwu Wang

Publications and source records attributed to Wenwu Wang.

At least 145 records · Page 8Linked to original sources

arXiv2022

On Metric Learning for Audio-Text Cross-Modal Retrieval

Audio-text retrieval aims at retrieving a target audio clip or caption from a pool of candidates given a query in another modality. Solving such cross-modal retrieval task is challenging because it not only requires learning robust feature representations for both modalities, but also requires capturing the fine-grained alignment between these two modalities. Existing cross-modal retrieval models are mostly optimized by metric learning objectives as both of them attempt to map data to an embedding space, where similar data are close together and dissimilar data are far apart. Unlike other cross-modal retrieval tasks such as image-text and video-text retrievals, audio-text retrieval is still an unexplored task. In this work, we aim to study the impact of different metric learning objectives on the audio-text retrieval task. We present an extensive evaluation of popular metric learning objectives on the AudioCaps and Clotho datasets. We demonstrate that NT-Xent loss adapted from self-supervised learning shows stable performance across different datasets and training settings, and outperforms the popular triplet-based losses. Our code is available at https://github.com/XinhaoMei/audio-text_retrieval.

eess.AS↗

arXiv2022

First-principles study of oxygen vacancy defects in orthorhombic Hf$_{0.5}$Zr$_{0.5}$O$_2$/SiO$_2$/Si gate stack

The gate defect of the ferroelectric HfO$_2$-based Si field-effect transistor (Si FeFET) plays a dominant role in its reliability issue. The first-principles calculations are an effective method for the atomic-scale understanding of gate defects. However, the first-principles study on the defects of FeFET gate stacks, i.e., metal/orthorhombic-Hf$_{0.5}$Zr$_{0.5}$O$_2$/SiO$_2$/Si structure, has not been reported so far. The key challenge is the construction of metal/orthorhombic-Hf$_{0.5}$Zr$_{0.5}$O$_2$/SiO$_2$/Si gate stack models. Here, we use the Hf$_{0.5}$Zr$_{0.5}$O$_2$(130) high-index crystal face as the orthorhombic ferroelectric layer and construct a robust atomic structure of the orthorhombic-Hf$_{0.5}$Zr$_{0.5}$O$_2$/SiO$_2$/Si gate stack without any gap states. Its high structural stability is ascribed to the insulated interface. The calculated band offsets show that this gate structure is of the type-I band alignment. Furthermore, the formation energies and charge transition levels (CTLs) of defects reveal that the oxygen vacancy defects are more favorable to form compared with other defects such as oxygen interstitial and Hf/Zr vacancy, and their CTLs are mainly localized near the Si conduction band minimum and valence band maximum, in agreement with the reported experimental results. The oxygen vacancy defects are responsible for charge trapping/de-trapping behavior in Si FeFET. This work provides an insight into gate defects and paves the way to carry out the first-principles study of ferroelectric HfO$_2$-based Si FeFET.

cond-mat.mtrl-sci↗

arXiv2022

A Mutual learning framework for Few-shot Sound Event Detection

Although prototypical network (ProtoNet) has proved to be an effective method for few-shot sound event detection, two problems still exist. Firstly, the small-scaled support set is insufficient so that the class prototypes may not represent the class center accurately. Secondly, the feature extractor is task-agnostic (or class-agnostic): the feature extractor is trained with base-class data and directly applied to unseen-class data. To address these issues, we present a novel mutual learning framework with transductive learning, which aims at iteratively updating the class prototypes and feature extractor. More specifically, we propose to update class prototypes with transductive inference to make the class prototypes as close to the true class center as possible. To make the feature extractor to be task-specific, we propose to use the updated class prototypes to fine-tune the feature extractor. After that, a fine-tuned feature extractor further helps produce better class prototypes. Our method achieves the F-score of 38.4$\%$ on the DCASE 2021 Task 5 evaluation set, which won the first place in the few-shot bioacoustic event detection task of Detection and Classification of Acoustic Scenes and Events (DCASE) 2021 Challenge.

cs.SD↗

arXiv2022

Anomalous Sound Detection using Spectral-Temporal Information Fusion

Unsupervised anomalous sound detection aims to detect unknown abnormal sounds of machines from normal sounds. However, the state-of-the-art approaches are not always stable and perform dramatically differently even for machines of the same type, making it impractical for general applications. This paper proposes a spectral-temporal fusion based self-supervised method to model the feature of the normal sound, which improves the stability and performance consistency in detection of anomalous sounds from individual machines, even of the same type. Experiments on the DCASE 2020 Challenge Task 2 dataset show that the proposed method achieved 81.39\%, 83.48\%, 98.22\% and 98.83\% in terms of the minimum AUC (worst-case detection performance amongst individuals) in four types of real machines (fan, pump, slider and valve), respectively, giving 31.79\%, 17.78\%, 10.42\% and 21.13\% improvement compared to the state-of-the-art method, i.e., Glow\_Aff. Moreover, the proposed method has improved AUC (average performance of individuals) for all the types of machines in the dataset. The source codes are available at https://github.com/liuyoude/STgram_MFN

cs.SD↗

arXiv2022

RaDur: A Reference-aware and Duration-robust Network for Target Sound Detection

Target sound detection (TSD) aims to detect the target sound from a mixture audio given the reference information. Previous methods use a conditional network to extract a sound-discriminative embedding from the reference audio, and then use it to detect the target sound from the mixture audio. However, the network performs much differently when using different reference audios (e.g. performs poorly for noisy and short-duration reference audios), and tends to make wrong decisions for transient events (i.e. shorter than $1$ second). To overcome these problems, in this paper, we present a reference-aware and duration-robust network (RaDur) for TSD. More specifically, in order to make the network more aware of the reference information, we propose an embedding enhancement module to take into account the mixture audio while generating the embedding, and apply the attention pooling to enhance the features of target sound-related frames and weaken the features of noisy frames. In addition, a duration-robust focal loss is proposed to help model different-duration events. To evaluate our method, we build two TSD datasets based on UrbanSound and Audioset. Extensive experiments show the effectiveness of our methods.

cs.SD↗

arXiv2022

Diverse Audio Captioning via Adversarial Training

Audio captioning aims at generating natural language descriptions for audio clips automatically. Existing audio captioning models have shown promising improvement in recent years. However, these models are mostly trained via maximum likelihood estimation (MLE),which tends to make captions generic, simple and deterministic. As different people may describe an audio clip from different aspects using distinct words and grammars, we argue that an audio captioning system should have the ability to generate diverse captions for a fixed audio clip and across similar audio clips. To address this problem, we propose an adversarial training framework for audio captioning based on a conditional generative adversarial network (C-GAN), which aims at improving the naturalness and diversity of generated captions. Unlike processing data of continuous values in a classical GAN, a sentence is composed of discrete tokens and the discrete sampling process is non-differentiable. To address this issue, policy gradient, a reinforcement learning technique, is used to back-propagate the reward to the generator. The results show that our proposed model can generate more diverse captions, as compared to state-of-the-art methods.

eess.AS↗

arXiv2022

Separate What You Describe: Language-Queried Audio Source Separation

In this paper, we introduce the task of language-queried audio source separation (LASS), which aims to separate a target source from an audio mixture based on a natural language query of the target source (e.g., "a man tells a joke followed by people laughing"). A unique challenge in LASS is associated with the complexity of natural language description and its relation with the audio sources. To address this issue, we proposed LASS-Net, an end-to-end neural network that is learned to jointly process acoustic and linguistic information, and separate the target source that is consistent with the language query from an audio mixture. We evaluate the performance of our proposed system with a dataset created from the AudioCaps dataset. Experimental results show that LASS-Net achieves considerable improvements over baseline methods. Furthermore, we observe that LASS-Net achieves promising generalization results when using diverse human-annotated descriptions as queries, indicating its potential use in real-world scenarios. The separated audio samples and source code are available at https://liuxubo717.github.io/LASS-demopage.

eess.AS↗

arXiv2022

Leveraging Pre-trained BERT for Audio Captioning

Audio captioning aims at using natural language to describe the content of an audio clip. Existing audio captioning systems are generally based on an encoder-decoder architecture, in which acoustic information is extracted by an audio encoder and then a language decoder is used to generate the captions. Training an audio captioning system often encounters the problem of data scarcity. Transferring knowledge from pre-trained audio models such as Pre-trained Audio Neural Networks (PANNs) have recently emerged as a useful method to mitigate this issue. However, there is less attention on exploiting pre-trained language models for the decoder, compared with the encoder. BERT is a pre-trained language model that has been extensively used in Natural Language Processing (NLP) tasks. Nevertheless, the potential of BERT as the language decoder for audio captioning has not been investigated. In this study, we demonstrate the efficacy of the pre-trained BERT model for audio captioning. Specifically, we apply PANNs as the encoder and initialize the decoder from the public pre-trained BERT models. We conduct an empirical study on the use of these BERT models for the decoder in the audio captioning model. Our models achieve competitive results with the existing audio captioning methods on the AudioCaps dataset.

eess.AS↗

arXiv2022

End-to-end translation of human neural activity to speech with a dual-dual generative adversarial network

In a recent study of auditory evoked potential (AEP) based brain-computer interface (BCI), it was shown that, with an encoder-decoder framework, it is possible to translate human neural activity to speech (T-CAS). However, current encoder-decoder-based methods achieve T-CAS often with a two-step method where the information is passed between the encoder and decoder with a shared dimension reduction vector, which may result in a loss of information. A potential approach to this problem is to design an end-to-end method by using a dual generative adversarial network (DualGAN) without dimension reduction of passing information, but it cannot realize one-to-one signal-to-signal translation (see Fig.1 (a) and (b)). In this paper, we propose an end-to-end model to translate human neural activity to speech directly, create a new electroencephalogram (EEG) datasets for participants with good attention by design a device to detect participants' attention, and introduce a dual-dual generative adversarial network (Dual-DualGAN) (see Fig. 1 (c) and (d)) to address an end-to-end translation of human neural activity to speech (ET-CAS) problem by group labelling EEG signals and speech signals, inserting a transition domain to realize cross-domain mapping. In the transition domain, the transition signals are cascaded by the corresponding EEG and speech signals in a certain proportion, which can build bridges for EEG and speech signals without corresponding features, and realize one-to-one cross-domain EEG-to-speech translation. The proposed method can translate word-length and sentence-length sequences of neural activity to speech. Experimental evaluation has been conducted to show that the proposed method significantly outperforms state-of-the-art methods on both words and sentences of auditory stimulus.

cs.SD↗

arXiv2022

Deep Neural Decision Forest for Acoustic Scene Classification

Acoustic scene classification (ASC) aims to classify an audio clip based on the characteristic of the recording environment. In this regard, deep learning based approaches have emerged as a useful tool for ASC problems. Conventional approaches to improving the classification accuracy include integrating auxiliary methods such as attention mechanism, pre-trained models and ensemble multiple sub-networks. However, due to the complexity of audio clips captured from different environments, it is difficult to distinguish their categories without using any auxiliary methods for existing deep learning models using only a single classifier. In this paper, we propose a novel approach for ASC using deep neural decision forest (DNDF). DNDF combines a fixed number of convolutional layers and a decision forest as the final classifier. The decision forest consists of a fixed number of decision tree classifiers, which have been shown to offer better classification performance than a single classifier in some datasets. In particular, the decision forest differs substantially from traditional random forests as it is stochastic, differentiable, and capable of using the back-propagation to update and learn feature representations in neural network. Experimental results on the DCASE2019 and ESC-50 datasets demonstrate that our proposed DNDF method improves the ASC performance in terms of classification accuracy and shows competitive performance as compared with state-of-the-art baselines.

eess.AS↗

arXiv2022

ARCA23K: An audio dataset for investigating open-set label noise

The availability of audio data on sound sharing platforms such as Freesound gives users access to large amounts of annotated audio. Utilising such data for training is becoming increasingly popular, but the problem of label noise that is often prevalent in such datasets requires further investigation. This paper introduces ARCA23K, an Automatically Retrieved and Curated Audio dataset comprised of over 23000 labelled Freesound clips. Unlike past datasets such as FSDKaggle2018 and FSDnoisy18K, ARCA23K facilitates the study of label noise in a more controlled manner. We describe the entire process of creating the dataset such that it is fully reproducible, meaning researchers can extend our work with little effort. We show that the majority of labelling errors in ARCA23K are due to out-of-vocabulary audio clips, and we refer to this type of label noise as open-set label noise. Experiments are carried out in which we study the impact of label noise in terms of classification performance and representation learning.

cs.SD↗

arXiv2022

An Audio-Based Deep Learning Framework For BBC Television Programme Classification

This paper proposes a deep learning framework for classification of BBC television programmes using audio. The audio is firstly transformed into spectrograms, which are fed into a pre-trained convolutional Neural Network (CNN), obtaining predicted probabilities of sound events occurring in the audio recording. Statistics for the predicted probabilities and detected sound events are then calculated to extract discriminative features representing the television programmes. Finally, the embedded features extracted are fed into a classifier for classifying the programmes into different genres. Our experiments are conducted over a dataset of 6,160 programmes belonging to nine genres labelled by the BBC. We achieve an average classification accuracy of 93.7% over 14-fold cross validation. This demonstrates the efficacy of the proposed framework for the task of audio-based classification of television programmes.

cs.SD↗

arXiv2021

CL4AC: A Contrastive Loss for Audio Captioning

Automated Audio captioning (AAC) is a cross-modal translation task that aims to use natural language to describe the content of an audio clip. As shown in the submissions received for Task 6 of the DCASE 2021 Challenges, this problem has received increasing interest in the community. The existing AAC systems are usually based on an encoder-decoder architecture, where the audio signal is encoded into a latent representation, and aligned with its corresponding text descriptions, then a decoder is used to generate the captions. However, training of an AAC system often encounters the problem of data scarcity, which may lead to inaccurate representation and audio-text alignment. To address this problem, we propose a novel encoder-decoder framework called Contrastive Loss for Audio Captioning (CL4AC). In CL4AC, the self-supervision signals derived from the original audio-text paired data are used to exploit the correspondences between audio and texts by contrasting samples, which can improve the quality of latent representation and the alignment between audio and texts, while trained with limited data. Experiments are performed on the Clotho dataset to show the effectiveness of our proposed approach.

eess.AS↗

arXiv2021

One to Multiple Mapping Dual Learning: Learning Multiple Sources from One Mixed Signal

Single channel blind source separation (SCBSS) refers to separate multiple sources from a mixed signal collected by a single sensor. The existing methods for SCBSS mainly focus on separating two sources and have weak generalization performance. To address these problems, an algorithm is proposed in this paper to separate multiple sources from a mixture by designing a parallel dual generative adversarial Network (PDualGAN) that can build the relationship between a mixture and the corresponding multiple sources to realize one-to-multiple cross-domain mapping. This algorithm can be applied to any mixed model such as linear instantaneous mixed model and convolutional mixed model. Besides, one-to-multiple datasets are created which including the mixtures and corresponding sources for this study. The experiment was carried out on four different datasets and tested with signals mixed in different proportions. Experimental results show that the proposed algorithm can achieve high performance in peak signal-to-noise ratio (PSNR) and correlation, which outperforms state-of-the-art algorithms.

cs.LG↗

arXiv2021

Conditional Sound Generation Using Neural Discrete Time-Frequency Representation Learning

Deep generative models have recently achieved impressive performance in speech and music synthesis. However, compared to the generation of those domain-specific sounds, generating general sounds (such as siren, gunshots) has received less attention, despite their wide applications. In previous work, the SampleRNN method was considered for sound generation in the time domain. However, SampleRNN is potentially limited in capturing long-range dependencies within sounds as it only back-propagates through a limited number of samples. In this work, we propose a method for generating sounds via neural discrete time-frequency representation learning, conditioned on sound classes. This offers an advantage in efficiently modelling long-range dependencies and retaining local fine-grained structures within sound clips. We evaluate our approach on the UrbanSound8K dataset, compared to SampleRNN, with the performance metrics measuring the quality and diversity of generated sounds. Experimental results show that our method offers comparable performance in quality and significantly better performance in diversity.

eess.AS↗

arXiv2021

Time-domain Speech Enhancement with Generative Adversarial Learning

Speech enhancement aims to obtain speech signals with high intelligibility and quality from noisy speech. Recent work has demonstrated the excellent performance of time-domain deep learning methods, such as Conv-TasNet. However, these methods can be degraded by the arbitrary scales of the waveform induced by the scale-invariant signal-to-noise ratio (SI-SNR) loss. This paper proposes a new framework called Time-domain Speech Enhancement Generative Adversarial Network (TSEGAN), which is an extension of the generative adversarial network (GAN) in time-domain with metric evaluation to mitigate the scaling problem, and provide model training stability, thus achieving performance improvement. In addition, we provide a new method based on objective function mapping for the theoretical analysis of the performance of Metric GAN, and explain why it is better than the Wasserstein GAN. Experiments conducted demonstrate the effectiveness of our proposed method, and illustrate the advantage of Metric GAN.

cs.SD↗

arXiv2021

An Encoder-Decoder Based Audio Captioning System With Transfer and Reinforcement Learning

Automated audio captioning aims to use natural language to describe the content of audio data. This paper presents an audio captioning system with an encoder-decoder architecture, where the decoder predicts words based on audio features extracted by the encoder. To improve the proposed system, transfer learning from either an upstream audio-related task or a large in-domain dataset is introduced to mitigate the problem induced by data scarcity. Besides, evaluation metrics are incorporated into the optimization of the model with reinforcement learning, which helps address the problem of ``exposure bias'' induced by ``teacher forcing'' training strategy and the mismatch between the evaluation metrics and the loss function. The resulting system was ranked 3rd in DCASE 2021 Task 6. Ablation studies are carried out to investigate how much each element in the proposed system can contribute to final performance. The results show that the proposed techniques significantly improve the scores of the evaluation metrics, however, reinforcement learning may impact adversely on the quality of the generated captions.

eess.AS↗

arXiv2021

Audio Captioning Transformer

Audio captioning aims to automatically generate a natural language description of an audio clip. Most captioning models follow an encoder-decoder architecture, where the decoder predicts words based on the audio features extracted by the encoder. Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are often used as the audio encoder. However, CNNs can be limited in modelling temporal relationships among the time frames in an audio signal, while RNNs can be limited in modelling the long-range dependencies among the time frames. In this paper, we propose an Audio Captioning Transformer (ACT), which is a full Transformer network based on an encoder-decoder architecture and is totally convolution-free. The proposed method has a better ability to model the global information within an audio signal as well as capture temporal relationships between audio events. We evaluate our model on AudioCaps, which is the largest audio captioning dataset publicly available. Our model shows competitive performance compared to other state-of-the-art approaches.

eess.AS↗