86 accepted papers
Dexterous grasp generation that considers armrelated constraints is crucial in real-world scenarios involving armenvironment collision avoidance, workspace boundary grasps, and consecutive grasping. Existing hand-centric grasp models, which primarily focus on the floating hand's pose, are insufficie
Instruction fine-tuning is a key technique for enhancing the performance of large language models (LLMs), but low-quality and redundant data often hinder its effectiveness. Recent studies suggest that filtering a small amount of high-quality data for instruction fine-tuning can achieve faster and mo…
While recent research has focused heavily on dexterous grasp pose generation, less attention has been devoted to the execution of planned grasps. Under shape and position uncertainty, open-loop execution often yields uncoordinated contacts, causing undesired in-hand object motion and even grasp fail…
Data-driven techniques enable modeling of nonlinear continuum robots directly from input-output data without relying on physics-based modeling. Among these techniques, the Koopman method has been particularly successful as it enables the application of linear optimal control techniques such as model
Audio-driven human animation has attracted wide attention thanks to its practical applications. However, critical challenges remain in generating high-resolution, long-duration videos with consistent appearance and natural hand motions. Existing methods extend videos using overlapping motion frames
Tool-integrated (TI) reinforcement learning (RL) enables large language models (LLMs) to perform multi-step reasoning by interacting with external tools such as search engines and retrievers. Group Relative Policy Optimization (GRPO), exemplified by the recent Search-R1, offers fast convergence and …
For a two-player imperfect-information extensive-form game (IIEFG) with $K$ time steps and a player action space of size $U$, the game tree complexity is $U^{2K}$, causing existing IIEFG solvers to struggle with large or infinite $(U,K)$, e.g., differential games with continuous action spaces. To pa…
Reinforcement learning with verifiable rewards has significantly advanced the reasoning capabilities of large language models, yet how to explicitly steer training toward exploration or exploitation remains an open problem. We introduce Token Hidden Reward (THR), a token-level metric that quantifies…
Training deep neural networks (DNNs) is a structured optimization problem, because the parameters are naturally represented by matrices and tensors rather than simple vectors. Under this structural representation, it has been widely observed that gradients are low-rank and Hessians are approximately…
Conversational Speech Synthesis (CSS) aims to align synthesized speech with the emotional and stylistic context of user-agent interactions to achieve empathy. Current generative CSS models face interpretability limitations due to insufficient emotional perception and redundant discrete speech coding…
Learning dynamics, which describes how the learning of specific training examples influences the model's predictions on other examples, gives us a powerful tool for understanding the behavior of deep learning systems. We study the learning dynamics of large language models during different types of…
Reinforcement learning (RL) has become popular in enhancing the reasoning capabilities of large language models (LLMs), with Group Relative Policy Optimization (GRPO) emerging as a widely used algorithm in recent systems. Despite GRPO's widespread adoption, we identify a previously unrecognized phen…
Koopman operator theory provides a powerful data-driven technique for modeling nonlinear dynamical systems in a linear framework, in comparison to computationally expensive and highly nonlinear physics-based simulations. However, Koopman operator-based models for soft robots are very high dimensiona
This paper explores successor features for knowledge transfer in zero-sum, complete-information, and turn-based games. Prior research in single-agent systems has shown that successor features can provide a "jump start" for agents when facing new tasks with varying reward structures. However, knowled
Connectors with latches, such as LC fiber connectors, RJ45 network cable connectors, and certain electronic connectors, have significant automation requirements for connection and disconnection. To accomplish not only the peg-in-hole but also the peg-out-hole tasks, careful consideration must be giv
Human motion generation aims to produce plausible human motion sequences according to various conditional inputs, such as text or audio. Despite the feasibility of existing methods in generating motion based on short prompts and simple motion patterns, they encounter difficulties when dealing with l…
Large language models (LLMs) have exhibited remarkable capabilities across a variety of domains and tasks, challenging our understanding of learning and cognition. Despite the recent success, current LLMs are not capable of processing complex audio information or conducting spoken conversations (lik…
With the widespread adoption of Large Language Models (LLMs), the prevalence of iterative interactions among these models is anticipated to increase. Notably, recent advancements in multi-round on-policy self-improving methods allow LLMs to generate new examples for training subsequent models. At th…
Conversational Speech Synthesis (CSS) aims to accurately express an utterance with the appropriate prosody and emotional inflection within a conversational setting. While recognising the significance of CSS task, the prior studies have not thoroughly investigated the emotional expressiveness problem…
Meta-learning enables rapid generalization to new tasks by learning knowledge from various tasks. It is intuitively assumed that as the training progresses, a model will acquire richer knowledge, leading to better generalization performance. However, our experiments reveal an unexpected result: ther…
Zero-shot text-to-speech (TTS) aims to synthesize voices with unseen speech prompts, which significantly reduces the data and computation requirements for voice cloning by skipping the fine-tuning process. However, the prompting mechanisms of zero-shot TTS still face challenges in the following aspe…
Talking face generation (TFG) aims to animate a target identity's face to create realistic talking videos. Personalized TFG is a variant that emphasizes the perceptual identity similarity of the synthesized result (from the perspective of appearance and talking style). While previous works typically…
Place recognition is an important task for robots and autonomous cars to localize themselves and close loops in pre-built maps. While single-modal sensor-based methods have shown satisfactory performance, cross-modal place recognition that retrieving images from a point-cloud database remains a chal…
One-shot 3D talking portrait generation aims to reconstruct a 3D avatar from an unseen image, and then animate it with a reference video or audio to generate a talking portrait video. The existing methods fail to simultaneously achieve the goals of accurate 3D avatar reconstruction and stable talkin…
We study zero-sum differential games with state constraints and one-sided information, where the informed player (Player 1) has a categorical payoff type unknown to the uninformed player (Player 2). The goal of Player 1 is to minimize his payoff without violating the constraints, while that of Playe…
Although much research has been done on proposing new models or loss functions to improve the generalisation of artificial neural networks (ANNs), less attention has been directed to the impact of the training data on generalisation. In this work, we start from approximating the interaction between…
Deep Neural Networks (DNNs) are currently predominantly trained using first-order methods. Some of these methods (e.g., Adam, AdaGrad, and RMSprop, and their variants) incorporate a small amount of curvature information by using a diagonal matrix to precondition the stochastic gradient. Recently, ef…
Direct speech-to-speech translation (S2ST) aims to convert speech from one language into another, and has demonstrated significant progress to date. Despite the recent success, current S2ST models still suffer from distinct degradation in noisy environments and fail to translate visual speech (i.e.,…
Finding Nash equilibrial policies for two-player differential games requires solving Hamilton-Jacobi-Isaacs (HJI) PDEs. Self-supervised learning has been used to approximate solutions of such PDEs while circumventing the curse of dimensionality. However, this method fails to learn discontinuous PDE…
Generative models have enabled the creation of contents that are indistinguishable from those taken from nature. Open-source development of such models raised concerns about the risks of their misuse for malicious purposes. One potential risk mitigation strategy is to attribute generative models via…
Unsupervised text-to-speech (TTS) aims to train TTS models for a specific language without any paired speech-text training data in that language. Existing methods either use speech and corresponding pseudo text generated by an unsupervised automatic speech recognition (ASR) model as training data, o…
Improving text representation has attracted much attention to achieve expressive text-to-speech (TTS). However, existing works only implicitly learn the prosody with masked token reconstruction tasks, which leads to low training efficiency and difficulty in prosody modeling. We propose CLAPSpeech, a…
To reduce the difficulty of annotation, partial label learning (PLL) has been widely studied, where each example is ambiguously annotated with a set of candidate labels instead of the exact correct label. PLL assumes that the candidate label set contains the correct label, which induces disambiguati…
Generative adversarial networks (GANs) and denoising diffusion probabilistic models (DDPMs) have recently achieved impressive performances in image and audio synthesis. After revisiting their success in conditional speech synthesis, we find that 1) GANs sacrifice sample diversity for quality and spe…
Stutter removal is an essential scenario in the field of speech editing. However, when the speech recording contains stutters, the existing text-based speech editing approaches still suffer from: 1) the over-smoothing problem in the edited speech; 2) lack of robustness due to the noise introduced by…
Generating photo-realistic video portraits with arbitrary speech audio is a crucial problem in film-making and virtual reality. Recently, several works explore the usage of neural radiance field (NeRF) in this task to improve 3D realness and image fidelity. However, the generalizability of previous…
In the era of deep learning, transferring information from a pretrained network to a downstream task by finetuning has many benefits. The choice of task head plays an important role in fine-tuning, as the pretrained and downstream tasks are usually different. Although there exist many different desi…
Compositional generalization, the ability of an agent to generalize to unseen combinations of latent factors, is easy for humans but hard for deep neural networks. A line of research in cognitive science has hypothesized a process, "iterated learning," to help explain how human language developed th…
Listening to long video/audio recordings from video conferencing and online courses for acquiring information is extremely inefficient. Even after ASR systems transcribe recordings into long-form spoken language documents, reading ASR transcripts only partly speeds up seeking information. It has bee…
Large-scale multimodal generative modeling has created milestones in text-to-image and text-to-video generation. Its application to audio still lags behind for two main reasons: the lack of large-scale datasets with high-quality text-audio pairs, and the complexity of modeling long continuous audio…
ICASSP2023 General Meeting Understanding and Generation Challenge (MUG) focuses on prompting a wide range of spoken language processing (SLP) research on meeting transcripts, as SLP applications are critical to improve users’ efficiency in grasping important information in meetings. MUG includes fiv…
Physics engines are essential components in simulating complex robotic systems. The accuracy and computational speed of these engines are crucial for reliable real-time simulation. This letter comprehensively evaluates the performance of five common physics engines, i.e., ODE, Bullet, DART, MuJoCo,
Expressive text-to-speech aims to generate high-quality samples with rich and diverse prosody, which is hampered by dual challenges: 1) prosodic attributes in highly dynamic voices are difficult to capture and model without intonation; and 2) highly multimodal prosodic representations cannot be well…
Direct speech-to-speech translation (S2ST) with discrete units leverages recent progress in speech representation learning. Specifically, a sequence of discrete representations derived in a self-supervised manner are predicted from the model and passed to a vocoder for speech reconstruction, while s…
Unsupervised video domain adaptation is a practical yet challenging task. In this work, for the first time, we tackle it from a disentanglement view. Our key idea is to handle the spatial and temporal domain divergence separately through disentanglement. Specifically, we consider the generation of c…
Video-to-sound generation aims to generate realistic and natural sound given a video input. However, previous video-to-sound generation methods can only generate a random or average timbre without any controls of the generated sound timbre, leading to the problem that people cannot obtain the desire…
It is difficult for non-autoregressive translation (NAT) models to capture the multi-modal distribution of target translations due to their conditional independence assumption, which is known as the “multi-modality problem”, including the lexical multi-modality and the syntactic multi-modality. Whil…
Generative models are now capable of synthesizing images, speeches, and videos that are hardly distinguishable from authentic contents. Such capabilities cause concerns such as malicious impersonation and IP theft. This paper investigates a solution for model attribution, i.e., the classification of…
Better-supervised models might have better performance. In this paper, we first clarify what makes for good supervision for a classification problem, and then explain two existing label refining methods, label smoothing and knowledge distillation, in terms of our proposed criterion. To further answe…
In this paper, we introduce DA <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula> , the first large-scale dual-arm dexterity-aware dataset for the generation of optimal bimanual grasp
Polyphone disambiguation aims to capture accurate pronunciation knowledge from natural text sequences for reliable Text-to-speech (TTS) systems. However, previous approaches require substantial annotated training data and additional efforts from language experts, making it difficult to extend high-q…
Singing voice synthesis (SVS) systems are built to synthesize high-quality and expressive singing voice, in which the acoustic model generates the acoustic features (e.g., mel-spectrogram) given a music score. Previous singing acoustic models adopt a simple loss (e.g., L1 and L2) or generative adver…
Zero-shot text-based singing editing enables singing voice modification based on the given edited lyrics without any additional data from the target singer. However, due to the different demands, challenges occur when applying existing speech editing methods to singing voice editing task, mainly inc…
Researchers are using deep learning models to explore the emergence of language in various language games, where agents interact and develop an emergent language to solve tasks. We focus on the factors that determine the expressivity of emergent languages, which reflects the amount of information ab…
Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hindered their applications to speech synthesis. This paper proposes FastDiff, a fast conditional diffusion model for high-qu…
Unconstrained lip-to-speech aims to generate corresponding speeches based on silent facial videos with no restriction to head pose or vocabulary. It is desirable to generate intelligible and natural speech with a fast speed in unconstrained settings. Currently, to handle the more complicated scena…
Style transfer for out-of-domain (OOD) speech synthesis aims to generate speech samples with unseen style (e.g., speaker identity, emotion, and prosody) derived from an acoustic reference, while facing the following challenges: 1) The highly dynamic style features in expressive voice are difficult t…
Building a high-fidelity speech synthesis system with noisy speech data is a challenging but valuable task, which could significantly reduce the cost of data collection. Existing methods usually train speech synthesis systems based on the speech denoised with an enhancement model or feed noise infor…
We are interested in a novel task, singing voice beautification (SVB). Given the singing voice of an amateur singer, SVB aims to improve the intonation and vocal tone of the voice, while keeping the content and vocal timbre. Current automatic pitch correction techniques are immature, and most of the…
The lack of publicly available high-quality and accurately labeled datasets has long been a major bottleneck for singing voice synthesis (SVS). To tackle this problem, we present M4Singer, a free-to-use Multi-style, Multi-singer Mandarin singing collection with elaborately annotated Musical scores a…
As a key component of talking face generation, lip movements generation determines the naturalness and coherence of the generated talking face video. Prior literature mainly focuses on speech-to-lip generation while there is a paucity in text-to-lip (T2L) generation. T2L is a challenging task and ex…
Expressive text-to-speech (TTS) has become a hot research topic recently, mainly focusing on modeling prosody in speech. Prosody modeling has several challenges: 1) the extracted pitch used in previous prosody modeling works have inevitable errors, which hurts the prosody modeling; 2) different attr…
Denoising Diffusion Probabilistic Models (DDPMs) can generate high-quality samples such as image and audio samples. However, DDPMs require hundreds to thousands of iterations to produce a sample. Several prior works have successfully accelerated DDPMs through adjusting the variance schedule (e.g., I…
Non-autoregressive text to speech (NAR-TTS) models have attracted much attention from both academia and industry due to their fast generation speed. One limitation of NAR-TTS models is that they ignore the correlation in time and frequency domains while generating speech mel-spectrograms, and thus c…
Neural networks have been widely applied in direction-of-arrival (DOA) estimation and source tracking systems. In this paper, we introduce a spherical convolutional recurrent neural network that utilizes Deepsphere, a graph-based spherical convolutional neural network, employing the steered response…
The recent progress in non-autoregressive text-to-speech (NAR-TTS) has made fast and high-quality speech synthesis possible. However, current NAR-TTS models usually use phoneme sequence as input and thus cannot understand the tree-structured syntactic information of the input sequence, which hurts t…
Recent studies demonstrated the vulnerability of control policies learned through deep reinforcement learning against adversarial attacks, raising concerns about the application of such models to risk-sensitive tasks such as autonomous driving. Threat models for these demonstrations are limited to (…
The performance of a camera network monitoring a set of targets depends crucially on the configuration of the cameras. In this paper, we investigate the reconfiguration strategy for the parameterized camera network model, with which the sensing qualities of the multiple targets can be optimized glob…
Growing applications of generative models have led to new threats such as malicious personation and digital copyright infringement. One solution to these threats is model attribution, i.e., the identification of user-end models where the contents under question are generated. Existing studies showe…
While neural-based text to speech (TTS) models can synthesize natural and intelligible voice, they usually require high-quality speech data, which is costly to collect. In many scenarios, only noisy speech of a target speaker is available, which presents challenges for TTS model training for this sp…
Non-autoregressive text to speech (TTS) models such as FastSpeech can synthesize speech significantly faster than previous autoregressive models with comparable quality. The training of FastSpeech model relies on an autoregressive teacher model for duration prediction (to provide more information as…
Federated learning enables collaborative training of machine learning models under strict privacy restrictions and federated text-to-speech aims to synthesize natural speech of multiple users with a few audio training samples stored in their devices locally. However, federated text-to-speech faces s…
Non-autoregressive text-to-speech (NAR-TTS) models such as FastSpeech 2 and Glow-TTS can synthesize high-quality speech from the given text in parallel. After analyzing two kinds of generative NAR-TTS models (VAE and normalizing flow), we find that: VAE is good at capturing the long-range semantics…
Automatic song writing aims to compose a song (lyric and/or melody) by machine, which is an interesting topic in both academia and industry. In automatic song writing, lyric-to-melody generation and melody-to-lyric generation are two important tasks, both of which usually suffer from the following c…
Despite the predominant use of first-order methods for training deep learning models, second-order methods, and in particular, natural gradient methods, remain of interest because of their potential for accelerating training through the use of curvature information. Several methods with non-diagonal…
Existing speech to speech translation systems heavily rely on the text of target language: they usually translate source language either to target text and then synthesize target speech from text, or directly to target speech with target text for auxiliary training. However, those methods cannot be…
Human-robot interactions (HRI) can be modeled as differential games with incomplete information, where each agent holds private reward parameters. Due to the open challenge in finding perfect Bayesian equilibria of such games, existing studies often decouple the belief and physical dynamics by itera…
The principle of compositionality, which enables natural language to represent complex concepts via a structured combination of simpler ones, allows us to convey an open-ended set of messages using a limited vocabulary. If compositionality is indeed a natural property of language, we may expect it t…
We consider the development of practical stochastic quasi-Newton, and in particular Kronecker-factored block diagonal BFGS and L-BFGS methods, for training deep neural networks (DNNs). In DNN training, the number of variables and components of the gradient n is often of the order of tens of million…
Non-autoregressive translation (NAT) achieves faster inference speed but at the cost of worse accuracy compared with autoregressive translation (AT). Since AT and NAT can share model structure and AT is an easier task than NAT due to the explicit dependency on previous target-side tokens, a natural…
Text to speech (TTS) and automatic speech recognition (ASR) are two dual tasks in speech processing and both achieve impressive performance thanks to the recent advance in deep learning and large amount of aligned speech and text data. However, the lack of aligned data poses a major practical proble…
Neural network based end-to-end text to speech (TTS) has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron 2) usually first generate mel-spectrogram from text, and then synthesize speech from the mel-spectrogram using vocoder such as WaveNet. Compared with t…
While intelligence of autonomous vehicles (AVs) has significantly advanced in recent years, accidents involving AVs suggest that these autonomous systems lack gracefulness in driving when interacting with human drivers. In the setting of a two-player game, we propose model predictive control based o…
Special high-end sensors with expensive hardware are usually needed to measure shock signals with high accuracy. In this paper, we show that cheap low-end sensors calibrated by deep neural networks are also capable to measure high-g shocks accurately. Firstly we perform drop shock tests to collect a…
Multilingual machine translation, which translates multiple languages with a single model, has attracted much attention due to its efficiency of offline training and online serving. However, traditional multilingual translation usually yields inferior accuracy compared with the counterpart using ind…
In this paper we introduce a design framework that permits task-specific complex geometries in robotic limbs with the minimal power consumption. Additionally we present a optimal gear ratio selection algorithm with realistic constraints, which we use as a subroutine within the geometry optimization.…