arXiv subjects

Jialu Li

Publications and source records attributed to Jialu Li.

At least 73 records · Page 4Linked to original sources

arXiv2023

DPATD: Dual-Phase Audio Transformer for Denoising

Recent high-performance transformer-based speech enhancement models demonstrate that time domain methods could achieve similar performance as time-frequency domain methods. However, time-domain speech enhancement systems typically receive input audio sequences consisting of a large number of time steps, making it challenging to model extremely long sequences and train models to perform adequately. In this paper, we utilize smaller audio chunks as input to achieve efficient utilization of audio information to address the above challenges. We propose a dual-phase audio transformer for denoising (DPATD), a novel model to organize transformer layers in a deep structure to learn clean audio sequences for denoising. DPATD splits the audio input into smaller chunks, where the input length can be proportional to the square root of the original sequence length. Our memory-compressed explainable attention is efficient and converges faster compared to the frequently used self-attention module. Extensive experiments demonstrate that our model outperforms state-of-the-art methods.

cs.SD↗

arXiv2023

DCHT: Deep Complex Hybrid Transformer for Speech Enhancement

Most of the current deep learning-based approaches for speech enhancement only operate in the spectrogram or waveform domain. Although a cross-domain transformer combining waveform- and spectrogram-domain inputs has been proposed, its performance can be further improved. In this paper, we present a novel deep complex hybrid transformer that integrates both spectrogram and waveform domains approaches to improve the performance of speech enhancement. The proposed model consists of two parts: a complex Swin-Unet in the spectrogram domain and a dual-path transformer network (DPTnet) in the waveform domain. We first construct a complex Swin-Unet network in the spectrogram domain and perform speech enhancement in the complex audio spectrum. We then introduce improved DPT by adding memory-compressed attention. Our model is capable of learning multi-domain features to reduce existing noise on different domains in a complementary way. The experimental results on the BirdSoundsDenoising dataset and the VCTK+DEMAND dataset indicate that our method can achieve better performance compared to state-of-the-art methods.

cs.SD↗

arXiv2023

Complex Image Generation SwinTransformer Network for Audio Denoising

Achieving high-performance audio denoising is still a challenging task in real-world applications. Existing time-frequency methods often ignore the quality of generated frequency domain images. This paper converts the audio denoising problem into an image generation task. We first develop a complex image generation SwinTransformer network to capture more information from the complex Fourier domain. We then impose structure similarity and detailed loss functions to generate high-quality images and develop an SDR loss to minimize the difference between denoised and clean audios. Extensive experiments on two benchmark datasets demonstrate that our proposed model is better than state-of-the-art methods.

cs.SD↗

arXiv2023

Scaling Data Generation in Vision-and-Language Navigation

Recent research in language-guided visual navigation has demonstrated a significant demand for the diversity of traversable environments and the quantity of supervision for training generalizable agents. To tackle the common data scarcity issue in existing vision-and-language navigation datasets, we propose an effective paradigm for generating large-scale data for learning, which applies 1200+ photo-realistic environments from HM3D and Gibson datasets and synthesizes 4.9 million instruction trajectory pairs using fully-accessible resources on the web. Importantly, we investigate the influence of each component in this paradigm on the agent's performance and study how to adequately apply the augmented data to pre-train and fine-tune an agent. Thanks to our large-scale dataset, the performance of an existing agent can be pushed up (+11% absolute with regard to previous SoTA) to a significantly new best of 80% single-run success rate on the R2R test split by simple imitation learning. The long-lasting generalization gap between navigating in seen and unseen environments is also reduced to less than 1% (versus 8% in the previous best method). Moreover, our paradigm also facilitates different models to achieve new state-of-the-art navigation results on CVDN, REVERIE, and R2R in continuous environments.

cs.CV↗

arXiv2023

High-resolution SOFIA/EXES Spectroscopy of Water Absorption Lines in the Massive Young Binary W3 IRS 5

We present in this paper mid-infrared (5-8~$μ$m) spectroscopy toward the massive young binary W3~IRS~5, using the EXES spectrometer in high-resolution mode ($R\sim$50,000) from the NASA Stratospheric Observatory for Infrared Astronomy (SOFIA). Many ($\sim$180) $ν_2$=1--0 and ($\sim$90) $ν_2$=2-1 absorption rovibrational transitions are identified. Two hot components over 500 K and one warm component of 190 K are identified through Gaussian fittings and rotation diagram analysis. Each component is linked to a CO component identified in the IRTF/iSHELL observations ($R$=88,100) through their kinematic and temperature characteristics. Revealed by the large scatter in the rotation diagram, opacity effects are important, and we adopt two curve-of-growth analyses, resulting in column densities of $\sim10^{19}$ cm$^{-2}$. In one analysis, the model assumes a foreground slab. The other assumes a circumstellar disk with an outward-decreasing temperature in the vertical direction. The disk model is favored because fewer geometry constraints are needed, although this model faces challenges as the internal heating source is unknown. We discuss the chemical abundances along the line of sight based on the CO-to-H$_2$O connection. In the hot gas, all oxygen not locked in CO resides in water. In the cold gas, we observe a substantial shortfall of oxygen and suggest that the potential carrier could be organics in solid ice.

astro-ph.GA↗

arXiv2023

PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation

Vision-and-Language Navigation (VLN) requires the agent to follow language instructions to navigate through 3D environments. One main challenge in VLN is the limited availability of photorealistic training environments, which makes it hard to generalize to new and unseen environments. To address this problem, we propose PanoGen, a generation method that can potentially create an infinite number of diverse panoramic environments conditioned on text. Specifically, we collect room descriptions by captioning the room images in existing Matterport3D environments, and leverage a state-of-the-art text-to-image diffusion model to generate the new panoramic environments. We use recursive outpainting over the generated images to create consistent 360-degree panorama views. Our new panoramic environments share similar semantic information with the original environments by conditioning on text descriptions, which ensures the co-occurrence of objects in the panorama follows human intuition, and creates enough diversity in room appearance and layout with image outpainting. Lastly, we explore two ways of utilizing PanoGen in VLN pre-training and fine-tuning. We generate instructions for paths in our PanoGen environments with a speaker built on a pre-trained vision-and-language model for VLN pre-training, and augment the visual observation with our panoramic environments during agents' fine-tuning to avoid overfitting to seen environments. Empirically, learning with our PanoGen environments achieves the new state-of-the-art on the Room-to-Room, Room-for-Room, and CVDN datasets. Pre-training with our PanoGen speaker data is especially effective for CVDN, which has under-specified instructions and needs commonsense knowledge. Lastly, we show that the agent can benefit from training with more generated panoramic environments, suggesting promising results for scaling up the PanoGen environments.

cs.CV↗

arXiv2023

Human Attention during Goal-directed Reading Comprehension Relies on Task Optimization

The computational principles underlying attention allocation in complex goal-directed tasks remain elusive. Goal-directed reading, i.e., reading a passage to answer a question in mind, is a common real-world task that strongly engages attention. Here, we investigate what computational models can explain attention distribution in this complex task. We show that the reading time on each word is predicted by the attention weights in transformer-based deep neural networks (DNNs) optimized to perform the same reading task. Eye-tracking further reveals that readers separately attend to basic text features and question-relevant information during first-pass reading and rereading, respectively. Similarly, text features and question relevance separately modulate attention weights in shallow and deep DNN layers. Furthermore, when readers scan a passage without a question in mind, their reading time is predicted by DNNs optimized for a word prediction task. Therefore, attention during real-world reading can be interpreted as the consequence of task optimization.

cs.CL↗

arXiv2023

Improving Vision-and-Language Navigation by Generating Future-View Image Semantics

Vision-and-Language Navigation (VLN) is the task that requires an agent to navigate through the environment based on natural language instructions. At each step, the agent takes the next action by selecting from a set of navigable locations. In this paper, we aim to take one step further and explore whether the agent can benefit from generating the potential future view during navigation. Intuitively, humans will have an expectation of how the future environment will look like, based on the natural language instructions and surrounding views, which will aid correct navigation. Hence, to equip the agent with this ability to generate the semantics of future navigation views, we first propose three proxy tasks during the agent's in-domain pre-training: Masked Panorama Modeling (MPM), Masked Trajectory Modeling (MTM), and Action Prediction with Image Generation (APIG). These three objectives teach the model to predict missing views in a panorama (MPM), predict missing steps in the full trajectory (MTM), and generate the next view based on the full instruction and navigation history (APIG), respectively. We then fine-tune the agent on the VLN task with an auxiliary loss that minimizes the difference between the view semantics generated by the agent and the ground truth view semantics of the next step. Empirically, our VLN-SIG achieves the new state-of-the-art on both the Room-to-Room dataset and the CVDN dataset. We further show that our agent learns to fill in missing patches in future views qualitatively, which brings more interpretability over agents' predicted actions. Lastly, we demonstrate that learning to predict future view semantics also enables the agent to have better performance on longer paths.

cs.CV↗

arXiv2022

BirdSoundsDenoising: Deep Visual Audio Denoising for Bird Sounds

Audio denoising has been explored for decades using both traditional and deep learning-based methods. However, these methods are still limited to either manually added artificial noise or lower denoised audio quality. To overcome these challenges, we collect a large-scale natural noise bird sound dataset. We are the first to transfer the audio denoising problem into an image segmentation problem and propose a deep visual audio denoising (DVAD) model. With a total of 14,120 audio images, we develop an audio ImageMask tool and propose to use a few-shot generalization strategy to label these images. Extensive experimental results demonstrate that the proposed model achieves state-of-the-art performance. We also show that our method can be easily generalized to speech denoising, audio separation, audio enhancement, and noise estimation.

cs.SD↗

arXiv2022

CLEAR: Improving Vision-Language Navigation with Cross-Lingual, Environment-Agnostic Representations

Vision-and-Language Navigation (VLN) tasks require an agent to navigate through the environment based on language instructions. In this paper, we aim to solve two key challenges in this task: utilizing multilingual instructions for improved instruction-path grounding and navigating through new environments that are unseen during training. To address these challenges, we propose CLEAR: Cross-Lingual and Environment-Agnostic Representations. First, our agent learns a shared and visually-aligned cross-lingual language representation for the three languages (English, Hindi and Telugu) in the Room-Across-Room dataset. Our language representation learning is guided by text pairs that are aligned by visual information. Second, our agent learns an environment-agnostic visual representation by maximizing the similarity between semantically-aligned image pairs (with constraints on object-matching) from different environments. Our environment agnostic visual representation can mitigate the environment bias induced by low-level visual information. Empirically, on the Room-Across-Room dataset, we show that our multilingual agent gets large improvements in all metrics over the strong baseline model when generalizing to unseen environments with the cross-lingual language representation and the environment-agnostic visual representation. Furthermore, we show that our learned language and visual representations can be successfully transferred to the Room-to-Room and Cooperative Vision-and-Dialogue Navigation task, and present detailed qualitative and quantitative generalization and grounding analysis. Our code is available at https://github.com/jialuli-luka/CLEAR

cs.CV↗

arXiv2022

High-Resolution M-band Spectroscopy of CO towards the Massive Young Stellar Binary W3 IRS5

We present in this paper the results of high spectral resolution ($R$=88,100) spectroscopy at 4.7 $μ$m with iSHELL/IRTF of hot molecular gas close to the massive binary protostar W3 IRS5. The binary was spatially resolved and the spectra of the two sources (MIR1 and MIR2) were obtained simultaneously for the first time. Hundreds of $^{12}$CO $ν$=0-1, $ν$=1-2 lines, and $ν$=0-1 transitions of the isotopes of $^{12}$CO were detected in absorption, and are blue-shifted compared to the cloud velocity $v_{LSR}=-$38 km/s. We decompose and identify kinematic components from the velocity profiles, and apply rotation diagram and curve of growth analyses to determine their physical properties. Temperatures and column densities of the identified components range from 30$-$700 K and 10$^{21}-$10$^{22}$ cm$^{-2}$, respectively. Our curve of growth analyses consider two scenarios. One assumes a foreground slab with a partial covering factor, which well reproduces the absorption of most of the components. The other assumes a circumstellar disk with an outward decreasing temperature in the vertical direction, and reproduces the absorption of all the hot components. We attribute the physical origins of the identified components to the foreground envelope ($<$100 K), post-J-shock regions (200$-$300 K), and clumpy structures on the circumstellar disks ($\sim$600 K). We propose that the components with a J-shock origin are akin to water maser spots in the same region, and are complementing the physical information of water masers along the direction of their movements.

astro-ph.GA↗

arXiv2022

Visualizations of Complex Sequences of Family-Infant Vocalizations Using Bag-of-Audio-Words Approach Based on Wav2vec 2.0 Features

In the U.S., approximately 15-17% of children 2-8 years of age are estimated to have at least one diagnosed mental, behavioral or developmental disorder. However, such disorders often go undiagnosed, and the ability to evaluate and treat disorders in the first years of life is limited. To analyze infant developmental changes, previous studies have shown advanced ML models excel at classifying infant and/or parent vocalizations collected using cell phone, video, or audio-only recording device like LENA. In this study, we pilot test the audio component of a new infant wearable multi-modal device that we have developed called LittleBeats (LB). LB audio pipeline is advanced in that it provides reliable labels for both speaker diarization and vocalization classification tasks, compared with other platforms that only record audio and/or provide speaker diarization labels. We leverage wav2vec 2.0 to obtain superior and more nuanced results with the LB family audio stream. We use a bag-of-audio-words method with wav2vec 2.0 features to create high-level visualizations to understand family-infant vocalization interactions. We demonstrate that our high-quality visualizations capture major types of family vocalization interactions, in categories indicative of mental, behavioral, and developmental health, for both labeled and unlabeled LB audio.

eess.AS↗

arXiv2022

EnvEdit: Environment Editing for Vision-and-Language Navigation

In Vision-and-Language Navigation (VLN), an agent needs to navigate through the environment based on natural language instructions. Due to limited available data for agent training and finite diversity in navigation environments, it is challenging for the agent to generalize to new, unseen environments. To address this problem, we propose EnvEdit, a data augmentation method that creates new environments by editing existing environments, which are used to train a more generalizable agent. Our augmented environments can differ from the seen environments in three diverse aspects: style, object appearance, and object classes. Training on these edit-augmented environments prevents the agent from overfitting to existing environments and helps generalize better to new, unseen environments. Empirically, on both the Room-to-Room and the multi-lingual Room-Across-Room datasets, we show that our proposed EnvEdit method gets significant improvements in all metrics on both pre-trained and non-pre-trained VLN agents, and achieves the new state-of-the-art on the test leaderboard. We further ensemble the VLN agents augmented on different edited environments and show that these edit methods are complementary. Code and data are available at https://github.com/jialuli-luka/EnvEdit

cs.CV↗

arXiv2021

Accent-Robust Automatic Speech Recognition Using Supervised and Unsupervised Wav2vec Embeddings

Speech recognition models often obtain degraded performance when tested on speech with unseen accents. Domain-adversarial training (DAT) and multi-task learning (MTL) are two common approaches for building accent-robust ASR models. ASR models using accent embeddings is another approach for improving robustness to accents. In this study, we perform systematic comparisons of DAT and MTL approaches using a large volume of English accent corpus (4000 hours of US English speech and 1244 hours of 20 non-US-English accents speech). We explore embeddings trained under supervised and unsupervised settings: a separate embedding matrix trained using accent labels, and embeddings extracted from a fine-tuned wav2vec model. We find that our DAT model trained with supervised embeddings achieves the best performance overall and consistently provides benefits for all testing datasets, and our MTL model trained with wav2vec embeddings are helpful learning accent-invariant features and improving novel/unseen accents. We also illustrate that wav2vec embeddings have more advantages for building accent-robust ASR when no accent labels are available for training supervised embeddings.

eess.AS↗

arXiv2021

Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic Information

Vision language navigation is the task that requires an agent to navigate through a 3D environment based on natural language instructions. One key challenge in this task is to ground instructions with the current visual information that the agent perceives. Most of the existing work employs soft attention over individual words to locate the instruction required for the next action. However, different words have different functions in a sentence (e.g., modifiers convey attributes, verbs convey actions). Syntax information like dependencies and phrase structures can aid the agent to locate important parts of the instruction. Hence, in this paper, we propose a navigation agent that utilizes syntax information derived from a dependency tree to enhance alignment between the instruction and the current visual scenes. Empirically, our agent outperforms the baseline model that does not use syntax information on the Room-to-Room dataset, especially in the unseen environment. Besides, our agent achieves the new state-of-the-art on Room-Across-Room dataset, which contains instructions in 3 languages (English, Hindi, and Telugu). We also show that our agent is better at aligning instructions with the current visual information via qualitative visualizations. Code and models: https://github.com/jialuli-luka/SyntaxVLN

cs.CL↗

arXiv2020

Exploring the Role of Argument Structure in Online Debate Persuasion

Online debate forums provide users a platform to express their opinions on controversial topics while being exposed to opinions from diverse set of viewpoints. Existing work in Natural Language Processing (NLP) has shown that linguistic features extracted from the debate text and features encoding the characteristics of the audience are both critical in persuasion studies. In this paper, we aim to further investigate the role of discourse structure of the arguments from online debates in their persuasiveness. In particular, we use the factor graph model to obtain features for the argument structure of debates from an online debating platform and incorporate these features to an LSTM-based model to predict the debater that makes the most convincing arguments. We find that incorporating argument structure features play an essential role in achieving the better predictive performance in assessing the persuasiveness of the arguments in online debates.

cs.CL↗

arXiv2020

Autosegmental Neural Nets: Should Phones and Tones be Synchronous or Asynchronous?

Phones, the segmental units of the International Phonetic Alphabet (IPA), are used for lexical distinctions in most human languages; Tones, the suprasegmental units of the IPA, are used in perhaps 70%. Many previous studies have explored cross-lingual adaptation of automatic speech recognition (ASR) phone models, but few have explored the multilingual and cross-lingual transfer of synchronization between phones and tones. In this paper, we test four Connectionist Temporal Classification (CTC)-based acoustic models, differing in the degree of synchrony they impose between phones and tones. Models are trained and tested multilingually in three languages, then adapted and tested cross-lingually in a fourth. Both synchronous and asynchronous models are effective in both multilingual and cross-lingual settings. Synchronous models achieve lower error rate in the joint phone+tone tier, but asynchronous training results in lower tone error rate.

eess.AS↗

arXiv2019

Investigating the Complex Velocity Structures within Dense Molecular Cloud Cores with GBT-Argus

We present the first results of high-spectral resolution (0.023 km/s) N$_2$H$^+$ observations of dense gas dynamics at core scales (~0.01 pc) using the recently commissioned Argus instrument on the Green Bank Telescope (GBT). While the fitted linear velocity gradients across the cores measured in our targets nicely agree with the well-known power-law correlation between the specific angular momentum and core size, it is unclear if the observed gradients represent core-scale rotation. In addition, our Argus data reveal detailed and intriguing gas structures in position-velocity (PV) space for all 5 targets studied in this project, which could suggest that the velocity gradients previously observed in many dense cores actually originate from large-scale turbulence or convergent flow compression instead of rigid-body rotation. We also note that there are targets in this study with their star-forming disks nearly perpendicular to the local velocity gradients, which, assuming the velocity gradient represents the direction of rotation, is opposite to what is described by the classical theory of star formation. This provides important insight on the transport of angular momentum within star-forming cores, which is a critical topic on studying protostellar disk formation.

astro-ph.GA↗