Yuexian Zou

Peking University | PKU · School of Electronic and Computer Engineering

Automatic radiology report generation has attracted enormous research interest due to its practical value in reducing the workload of radiologists. However, simultaneously establishing global correspondences between the image (e.g., Chest X-ray) and its related report and local alignments between image patches and keywords remains challenging. To t...

Natural Language Generation (NLG) accepts input data in the form of images, videos, or text and generates corresponding natural language text as output. Existing NLG methods mainly adopt a supervised approach and rely heavily on coupled data-to-text pairs. However, for many targeted scenarios and for non-English languages, sufficient quantities of...

Multi-turn response selection is a challenging task due to its high demands on efficient extraction of the matching features from abundant information provided by context utterances. Since incorporating syntactic information like dependency structures into neural models can promote a better understanding of the sentences, such a method has been wid...

Natural Language Generation (NLG) accepts input data in the form of images, videos, or text and generates corresponding natural language text as output. Existing NLG methods mainly adopt a supervised approach and rely heavily on coupled data-to-text pairs. However, for many targeted scenarios and for non-English languages, sufficient quantities of...

Existing weakly supervised sound event detection (WSSED) work has not explored both types of co-occurrences simultaneously, i.e., some sound events often co-occur, and their occurrences are usually accompanied by specific background sounds, so they would be inevitably entangled, causing misclassification and biased localization results with only cl...

Knowledge-aware question answering (KAQA) requires the model to answer questions over a knowledge base, which is essential for both open-domain QA and domain-specific QA, especially when language models alone cannot provide all the knowledge needed. Despite the promising result of recent KAQA systems which tend to integrate linguistic knowledge fro...

Learning representations for graph-structured data is essential for graph analytical tasks. While remarkable progress has been made on static graphs, researches on temporal graphs are still in its beginning stage. The bottleneck of the temporal graph representation learning approach is the neighborhood aggregation strategy, based on which graph att...

With the rise of short videos, the demand for selecting appropriate background music (BGM) for a video has increased significantly, video-music retrieval (VMR) task gradually draws much attention by research community. As other cross-modal learning tasks, existing VMR approaches usually attempt to measure the similarity between the video and music...

Video grounding aims to locate a moment of interest matching the given query sentence from an untrimmed video. Previous works ignore the \emph{sparsity dilemma} in video annotations, which fails to provide the context information between potential events and query sentences in the dataset. In this paper, we contend that providing easily available c...

Recently, frequency domain all-neural beamforming methods have achieved remarkable progress for multichannel speech separation. In parallel, the integration of time domain network structure and beamforming also gains significant attention. This study proposes a novel all-neural beamforming method in time domain and makes an attempt to unify the all...

How to solve the data scarcity problem for end-to-end speech-to-text translation (ST)? It's well known that data augmentation is an efficient method to improve performance for many tasks by enlarging the dataset. In this paper, we propose Mix at three levels for Speech Translation (M^3ST) method to increase the diversity of the augmented training c...

Graph convolutional networks (GCNs) are widely adopted in skeleton-based action recognition due to their powerful ability to model data topology. We argue that the performance of recent proposed skeleton-based action recognition methods is limited by the following factors. First, the predefined graph structures are shared throughout the network, la...

Training supervised video captioning model requires coupled video-caption pairs. However, for many targeted languages, sufficient paired data are not available. To this end, we introduce the unpaired video captioning task aiming to train models without coupled video-caption pairs in target language. To solve the task, a natural choice is to employ...

Multi-intent detection and slot filling joint models are gaining increasing traction since they are closer to complicated real-world scenarios. However, existing approaches (1) focus on identifying implicit correlations between utterances and one-hot encoded labels in both tasks while ignoring explicit label characteristics; (2) directly incorporat...

Expressive text-to-speech (TTS) can synthesize a new speaking style by imiating prosody and timbre from a reference audio, which faces the following challenges: (1) The highly dynamic prosody information in the reference audio is difficult to extract, especially, when the reference audio contains background noise. (2) The TTS systems should have go...

Video-Text Pre-training (VTP) aims to learn transferable representations for various downstream tasks from large-scale web videos. To date, almost all existing VTP methods are limited to retrieval-based downstream tasks, e.g., video retrieval, whereas their transfer potentials on localization-based tasks, e.g., temporal grounding, are under-explore...

Vision-and-language (V-L) tasks require the system to understand both vision content and natural language, thus learning fine-grained joint representations of vision and language (a.k.a. V-L representations) is of paramount importance. Recently, various pre-trained V-L models are proposed to learn V-L representations and achieve improved results in...

For video captioning, “pre-training and fine-tuning” has become a de facto paradigm, where ImageNet Pre-training (INP) is usually used to encode the video content, then a task-oriented network is fine-tuned from scratch to cope with caption generation. This paper first investigates the impact of the recently proposed CLIP (Contrastive Language-Imag...

Mainstream video captioning models (VCMs) are trained under fully supervised learning that relies heavily on large-scaled high-quality video-caption pairs. Unfortunately, evaluating the corpora of benchmark datasets shows that there are many defects associated with humanly labeled annotations, such as variation of the caption length and quality for...

Video Referring Expression Comprehension (REC) aims to localize a target object in video frames referred by the natural language expression. Recently, the Transformerbased methods have greatly boosted the performance limit. However, we argue that the current query design is suboptima and suffers from two drawbacks: 1) the slow training convergence...

This technical report presents the 1st winning model for Financial Community Question-and-Answering (FCQA), which is a task newly introduced in the Challenge of Financial QA under Marker Volatility in WAIC 2022. FCQA aims to respond to the user's queries in the financial forums with the assistance of heterogeneous knowledge sources. We address this...

Weakly-Supervised Temporal Action Localization (WSTAL) aims to localize actions in untrimmed videos with only video-level labels. Currently, most state-of-the-art WSTAL methods follow a Multi-Instance Learning (MIL) pipeline: producing snippet-level predictions first and then aggregating to the video-level prediction. However, we argue that existin...

Unsupervised video captioning aims to describe videos from unlabeled videos and sentence corpus without the reliance on human annotated video-sentence pairs. A straightforward manner is to borrow the merit from unsupervised image captioning methods, which resort to pseudo captions retrieved by visual concepts detected in image. However, directly ap...

We investigate the problem of video Referring Expression Comprehension (REC), which aims to localize the referent objects described in the sentence to visual regions in the video frames. Despite the recent progress, existing methods suffer from two problems: 1) inconsistent localization results across video frames; 2) confusion between the referent...

Generating sound effects that humans want is an important topic. However, there are few studies in this area for sound generation. In this study, we investigate generating sound conditioned on a text prompt and propose a novel text-to-sound generation framework that consists of a text encoder, a Vector Quantized Variational Autoencoder (VQ-VAE), a...

Recently, attention-based models for joint intent detection and slot filling have achieved state-of-the-art performance. However, we think the conventional attention can only capture the first-order feature interaction between two tasks and is insufficient. To address this issue, we propose a unified BiLinear attention block, which leverages biline...

Despite the rapid progress in automatic speech recognition (ASR) research, recognizing multilingual speech using a unified ASR system remains highly challenging. Previous works on multilingual speech recognition mainly focus on two directions: recognizing multiple monolingual speech or recognizing code-switched speech that uses different languages...

Hand-crafted spatial features, such as inter-channel intensity difference (IID) and inter-channel phase difference (IPD), play a fundamental role in recent deep learning based dual-microphone speech enhancement (DMSE) systems. However, learning the mutual relationship between artificially designed spatial and spectral features is hard in the end-to...

In spoken question answering, the systems are designed to answer questions from contiguous text spans within the related speech transcripts. However, the most natural way that human seek or test their knowledge is via human conversations. Therefore, we propose a new Spoken Conversational Question Answering task (SCQA), aiming at enabling the system...

Dominant researches adopt supervised training for speaker extraction, while the scarcity of ideally clean corpus and channel mismatch problem are rarely considered. To this end, we propose speaker-aware mixture of mixtures training (SAMoM), utilizing the consistency of speaker identity among target source, enrollment utterance and target estimate t...

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 usi...

Target sound detection (TSD) aims to detect the target sound from mixture audio given the reference information. Previous work shows that a good detection performance relies on fully-annotated data. However, collecting fully-annotated data is labor-extensive. Therefore, we consider TSD with mixed supervision, which learns novel categories (target d...

Recently, end-to-end speaker extraction has attracted increasing attention and shown promising results. However, its performance is often inferior to that of a blind source separation (BSS) counterpart with a similar network architecture, due to the auxiliary speaker encoder may sometimes generate ambiguous speaker embeddings. Such ambiguous guidan...

Target sound extraction (TSE) aims to extract the sound part of a target sound event class from a mixture audio with multiple sound events. The previous works mainly focus on the problems of weakly-labelled data, jointly learning and new classes, however, no one cares about the onset and offset times of the target sound event, which has been emphas...

Keyword spotting (KWS) and speaker verification (SV) are two important tasks in speech applications. Research shows that the state-of-art KWS and SV models are trained independently using different datasets since they expect to learn distinctive acoustic features. However, humans can distinguish language content and the speaker identity simultaneou...

Graph convolutional networks (GCNs) are widely adopted in skeleton-based action recognition due to their powerful ability to model data topology. We argue that the performance of recent proposed skeleton-based action recognition methods is limited by the following factors. First, the predefined graph structures are shared throughout the network, la...

In automatic speech recognition (ASR) research, discriminative criteria have achieved superior performance in DNN-HMM systems. Given this success, the adoption of discriminative criteria is promising to boost the performance of end-to-end (E2E) ASR systems. With this motivation, previous works have introduced the minimum Bayesian risk (MBR, one of...

Despite the rapid progress of end-to-end (E2E) automatic speech recognition (ASR), it has been shown that incorporating external language models (LMs) into the decoding can further improve the recognition performance of E2E ASR systems. To align with the modeling units adopted in E2E ASR systems, subword-level (e.g., characters, BPE) LMs are usuall...

Despite the rapid progress of end-to-end (E2E) automatic speech recognition (ASR), it has been shown that incorporating external language models (LMs) into the decoding can further improve the recognition performance of E2E ASR systems. To align with the modelingunits adopted in E2E ASR systems, subword-level (e.g., characters, BPE) LMs are usually...

A portion of the data in video captioning datasets are noisy and unsuitable for models to learn at early stages, e.g., there could be a generic 4-word-long caption lacking distinctive details of video content and a 19-word-long description with rare words and complex structure given the average caption length of around 9. The conventional training...

In automatic speech recognition (ASR) research, discriminative criteria have achieved superior performance in DNN-HMM systems. Given this success, the adoption of discriminative criteria is promising to boost the performance of end-to-end (E2E) ASR systems. With this motivation, previous works have introduced the minimum Bayesian risk (MBR, one of...

Recently, frequency domain all-neural beamforming methods have achieved remarkable progress for multichannel speech separation. In parallel, the integration of time domain network structure and beamforming also gains significant attention. This study proposes a novel all-neural beamforming method in time domain and makes an attempt to unify the all...

Human beings can perceive a target sound that we are interested in from a multi-source environment by the selective auditory attention, however, such functionality was hardly ever explored in machine hearing.This paper address the target sound detection (TSD), which aims to detect the target sound signal from a mixture audio when a target sound's r...

Recently, End-to-End (E2E) frameworks have achieved remarkable results on various Automatic Speech Recognition (ASR) tasks. However, Lattice-Free Maximum Mutual Information (LF-MMI), as one of the discriminative training criteria that show superior performance in hybrid ASR systems, is rarely adopted in E2E ASR frameworks. In this work, we propose...

Training supervised video captioning model requires coupled video-caption pairs. However, for many targeted languages, sufficient paired data are not available. To this end, we introduce the unpaired video captioning task aiming to train models without coupled video-caption pairs in target language. To solve the task, a natural choice is to employ...

For video captioning, "pre-training and fine-tuning" has become a de facto paradigm, where ImageNet Pre-training (INP) is usually used to help encode the video content, and a task-oriented network is fine-tuned from scratch to cope with caption generation. Comparing INP with the recently proposed CLIP (Contrastive Language-Image Pre-training), this...

Human-Object Interaction (HOI) detection devotes to learn how humans interact with surrounding objects via inferring triplets of $\langle $ human, verb, object $\rangle $ . Recent HOI detection methods infer HOIs by directly extracting appearance features and spatial configuration from related visual targets of human and object, but neglect pow...

The task of Human-Object Interaction (HOI) detection devotes to learn how humans interact with surrounding objects via inferring fine-grained triplets of $\langle $ human, verb, object $\rangle $ . Most HOI feature learning techniques are dependent on pre-detected instance regions or human body-part regions, which are computationally expensive a...

Automated audio captioning (AAC) has developed rapidly in recent years, involving acoustic signal processing and natural language processing to generate human-readable sentences for audio clips. The current models are generally based on the neural encoder-decoder architecture, and their decoder mainly uses acoustic information that is extracted fro...

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 featur...

Acoustic feature extraction (AFE) is considered as one of the most challenging techniques for speech applications since the adverse environment noises always cause significant variation on the extracted acoustic features. In this paper, we propose a systematical AFE approach which based on stacked denoising auto encoder (SDAE) aiming at extracting...

Temporal modeling in videos is crucial for action recognition. Traditionally, it involves feature aggregation for both local motion and global semantic. In this paper, we propose an Efficient Action Recognition network (EAR), which includes a Persistence of Appearance (PA) module and a Various-timescale Aggregation (VA) module for local and global...

Intent detection (ID) and Slot filling (SF) are two major tasks in spoken language understanding (SLU). Recently, attention mechanism has been shown to be effective in jointly optimizing these two tasks in an interactive manner. However, latest attention-based works concentrated only on the first-order attention design, while ignoring the explorati...

Video grounding aims to localize the temporal segment corresponding to a sentence query from an untrimmed video. Almost all existing video grounding methods fall into two frameworks: 1) Top-down model: It predefines a set of segment candidates and then conducts segment classification and regression. 2) Bottom-up model: It directly predicts frame-wi...

Spoken question answering (SQA) requires fine-grained understanding of both spoken documents and questions for the optimal answer prediction. In this paper, we propose novel training schemes for spoken question answering with a self-supervised training stage and a contrastive representation learning stage. In the self-supervised stage, we propose t...

Intent detection and slot filling are two main tasks in natural language understanding (NLU) for identifying users' needs from their utterances. These two tasks are highly related and often trained jointly. However, most previous works assume that each utterance only corresponds to one intent, ignoring the fact that a user utterance in many cases c...

Weakly-Supervised Temporal Action Localization (WSTAL) aims to localize actions in untrimmed videos with only video-level labels. Currently, most state-of-the-art WSTAL methods follow a Multi-Instance Learning (MIL) pipeline: producing snippet-level predictions first and then aggregating to the video-level prediction. However, we argue that existin...

Keyword Spotting (KWS) remains challenging to achieve the trade-off between small footprint and high accuracy. Recently proposed metric learning approaches improved the generalizability of models for the KWS task, and 1D-CNN based KWS models have achieved the state-of-the-arts (SOTA) in terms of model size. However, for metric learning, due to data...

Spoken question answering (SQA) has recently drawn considerable attention in the speech community. It requires systems to find correct answers from the given spoken passages simultaneously. The common SQA systems consist of the automatic speech recognition (ASR) module and text-based question answering module. However, previous methods suffer from...

Human-Object Interaction (HOI) detection devotes to learn how humans interact with surrounding objects. Latest end-to-end HOI detectors are short of relation reasoning, which leads to inability to learn HOI-specific interactive semantics for predictions. In this paper, we therefore propose novel relation reasoning for HOI detection. We first presen...