论文检索

Applications · Language, Speech and Dialog

Haozhe Ji, Pei Ke, Hongning Wang, Minlie Huang

Despite the remarkable advances in language modeling, current mainstream decoding methods still struggle to generate texts that align with human texts across different aspects. In particular, sampling-based methods produce less-repetitive texts which are often disjunctive in discourse, while search-based methods maintain topic coherence at the cost of increased repetition. Overall, these methods fall short in achieving holistic alignment across a broad range of aspects. In this work, we frame decoding from a language model as an optimization problem with the goal of strictly matching the expected performance with human texts measured by multiple metrics of desired aspects simultaneously. The resulting decoding distribution enjoys an analytical solution that scales the input language model distribution via a sequence-level energy function defined by these metrics. And most importantly, we prove that this induced distribution is guaranteed to improve the perplexity on human texts, which suggests a better approximation to the underlying distribution of human texts. To facilitate tractable sampling from this globally normalized distribution, we adopt the Sampling-Importance-Resampling technique. Experiments on various domains and model scales demonstrate the superiority of our method in metrics alignment with human texts and human evaluation over strong baselines.

Applications · Language, Speech and Dialog

Alexander Liu, Matthew Le, Apoorv Vyas, Bowen Shi, Andros Tjandra, Wei-Ning Hsu

Generative models have gained more and more attention in recent years for their remarkable success in tasks that required estimating and sampling data distribution to generate high-fidelity synthetic data. In speech, text-to-speech synthesis and neural vocoder are good examples where generative models have shined. While generative models have been applied to different applications in speech, there exists no general-purpose generative model that models speech directly. In this work, we take a step toward this direction by showing a single pre-trained generative model can be adapted to different downstream tasks with strong performance. Specifically, we pre-trained a generative model, named SpeechFlow, on 60k hours of untranscribed speech with Flow Matching and masked conditions. Experiment results show the pre-trained generative model can be fine-tuned with task-specific data to match or surpass existing expert models on speech enhancement, separation, and synthesis. Our work suggested a foundational model for generation tasks in speech can be built with generative pre-training.

Deep Learning · Algorithms

Jae-Hong Lee, Joon-Hyuk Chang

Deep neural networks (DNNs) have revolutionized tasks such as image classification and speech recognition but often falter when training and test data diverge in distribution. External factors, from weather effects on images to varied speech environments, can cause this discrepancy, compromising DNN performance. Online test-time adaptation (OTTA) methods present a promising solution, recalibrating models in real-time during the test stage without requiring historical data. However, the OTTA paradigm is imperfect, often falling prey to issues such as catastrophic forgetting due to its reliance on noisy, self-trained predictions. Although some contemporary strategies mitigate this by tying adaptations to the static source model, this restricts model flexibility. This paper introduces a continual momentum filtering (CMF) framework, leveraging the Kalman filter (KF) to strike a balance between model adaptability and information retention. The CMF intertwines optimization via stochastic gradient descent with a KF-based inference process. This methodology not only aids in averting catastrophic forgetting but also provides high adaptability to shifting data distributions. We validate our framework on various OTTA scenarios and real-world situations regarding covariate and label shifts, and the CMF consistently shows superior performance compared to state-of-the-art methods.

Social Aspects · Trustworthy Machine Learning

Fei Kong, Jinhao Duan, ruipeng ma, Heng Tao Shen, Xiaoshuang Shi, Xiaofeng Zhu, Kaidi Xu

Recently, diffusion models have achieved remarkable success in generating tasks, including image and audio generation. However, like other generative models, diffusion models are prone to privacy issues. In this paper, we propose an efficient query-based membership inference attack (MIA), namely Proximal Initialization Attack (PIA), which utilizes groundtruth trajectory obtained by $\epsilon$ initialized in $t=0$ and predicted point to infer memberships. Experimental results indicate that the proposed method can achieve competitive performance with only two queries that achieve at least 6$\times$ efficiency than the previous SOTA baseline on both discrete-time and continuous-time diffusion models. Moreover, previous works on the privacy of diffusion models have focused on vision tasks without considering audio tasks. Therefore, we also explore the robustness of diffusion models to MIA in the text-to-speech (TTS) task, which is an audio generation task. To the best of our knowledge, this work is the first to study the robustness of diffusion models to MIA in the TTS task. Experimental results indicate that models with mel-spectrogram (image-like) output are vulnerable to MIA, while models with audio output are relatively robust to MIA. Code is available at https://github.com/kong13661/PIA.

Applications · Language, Speech and Dialog

Xuhui Zhou, Hao Zhu, Leena Mathur, Ruohong Zhang, Haofei Yu, Zhengyang Qi, Louis-Philippe Morency, Yonatan Bisk, Daniel Fried, Graham Neubig 等

*Humans are social beings*; we pursue social goals in our daily interactions, which is a crucial aspect of social intelligence. Yet, AI systems' abilities in this realm remain elusive. We present SOTOPIA, an open-ended environment to simulate complex social interactions between artificial agents and evaluate their social intelligence. In our environment, agents role-play and *interact* under a wide variety of scenarios; they coordinate, collaborate, exchange, and compete with each other to achieve complex social goals. We simulate the role-play interaction between LLM-based agents and humans within this task space and evaluate their performance with a holistic evaluation framework called SOTOPIA-Eval. With SOTOPIA, we find significant differences between these models in terms of their social intelligence, and we identify a subset of SOTOPIA scenarios, SOTOPIA-hard, that is generally challenging for all models. We find that on this subset, GPT-4 achieves a significantly lower goal completion rate than humans and struggles to exhibit social commonsense reasoning and strategic communication skills. These findings demonstrate SOTOPIA's promise as a general platform for research on evaluating and improving social intelligence in artificial agents.

Applications · Language, Speech and Dialog

Weize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Chi-Min Chan, Heyang Yu, Yaxi Lu, Yi-Hsin Hung, Chen Qian 等

Autonomous agents empowered by Large Language Models (LLMs) have undergone significant improvements, enabling them to generalize across a broad spectrum of tasks. However, in real-world scenarios, cooperation among individuals is often required to enhance the efficiency and effectiveness of task accomplishment. Hence, inspired by human group dynamics, we propose a multi-agent framework AgentVerse that can effectively orchestrate a collaborative group of expert agents as a greater-than-the-sum-of-its-parts system. Our experiments demonstrate that AgentVerse can proficiently deploy multi-agent groups that outperform a single agent. Extensive experiments on text understanding, reasoning, coding, tool utilization, and embodied AI confirm the effectiveness of AgentVerse. Moreover, our analysis of agent interactions within AgentVerse reveals the emergence of specific collaborative behaviors, contributing to heightened group efficiency. We will release our codebase, AgentVerse, to further facilitate multi-agent research.

Applications · Language, Speech and Dialog

Zengwei Yao, Liyong Guo, Xiaoyu Yang, Wei Kang, Fangjun Kuang, Yifan Yang, Zengrui Jin, Long Lin, Daniel Povey

The Conformer has become the most popular encoder model for automatic speech recognition (ASR). It adds convolution modules to a transformer to learn both local and global dependencies. In this work we describe a faster, more memory-efficient, and better-performing transformer, called Zipformer. Modeling changes include: 1) a U-Net-like encoder structure where middle stacks operate at lower frame rates; 2) reorganized block structure with more modules, within which we re-use attention weights for efficiency; 3) a modified form of LayerNorm called BiasNorm allows us to retain some length information; 4) new activation functions SwooshR and SwooshL work better than Swish. We also propose a new optimizer, called ScaledAdam, which scales the update by each tensor's current scale to keep the relative change about the same, and also explictly learns the parameter scale. It achieves faster converge and better performance than Adam. Extensive experiments on LibriSpeech, Aishell-1, and WenetSpeech datasets demonstrate the effectiveness of our proposed Zipformer over other state-of-the-art ASR models. Our code is publicly available at https://github.com/k2-fsa/icefall.

Applications · Language, Speech and Dialog

Ryan Wong, Necati Cihan Camgoz, Richard Bowden

Automatic Sign Language Translation requires the integration of both computer vision and natural language processing to effectively bridge the communication gap between sign and spoken languages. However, the deficiency in large-scale training data to support sign language translation means we need to leverage resources from spoken language. We introduce, Sign2GPT, a novel framework for sign language translation that utilizes large-scale pretrained vision and language models via lightweight adapters for gloss-free sign language translation. The lightweight adapters are crucial for sign language translation, due to the constraints imposed by limited dataset sizes and the computational requirements when training with long sign videos.We also propose a novel pretraining strategy that directs our encoder to learn sign representations from automatically extracted pseudo-glosses without requiring gloss order information or annotations.We evaluate our approach on two public benchmark sign language translation datasets, namely RWTH-PHOENIX-Weather 2014T and CSL-Daily, and improve on state-of-the-art gloss-free translation performance with a significant margin.

Xize Cheng, Tao Jin, Rongjie Huang, Linjun Li, Wang Lin, Zehan Wang, Ye Wang, Huadai Liu, Aoxiong Yin, Zhou Zhao

Multi-media communications facilitate global interaction among people. However, despite researchers exploring cross-lingual translation techniques such as machine translation and audio speech translation to overcome language barriers, there is still a shortage of cross-lingual studies on visual speech. This lack of research is mainly due to the absence of datasets containing visual speech and translated text pairs. In this paper, we present AVMuST-TED, the first dataset for Audio-Visual Multilingual Speech Translation, derived from TED talks. Nonetheless, visual speech is not as distinguishable as audio speech, making it difficult to develop a mapping from source speech phonemes to the target language text. To address this issue, we propose MixSpeech, a cross-modality self-learning framework that utilizes audio speech to regularize the training of visual speech tasks. To further minimize the cross-modality gap and its impact on knowledge transfer, we suggest adopting mixed speech, which is created by interpolating audio and visual streams, along with a curriculum learning strategy to adjust the mixing ratio as needed. MixSpeech enhances speech translation in noisy environments, improving BLEU scores for four languages on AVMuST-TED by +1.4 to +4.2. Moreover, it achieves state-of-the-art performance in lip reading on CMLR (11.1%), LRS2 (25.5%), and LRS3 (28.0%).

Xiuzhe Wu, Pengfei Hu, Yang Wu, Xiaoyang Lyu, Yan-Pei Cao, Ying Shan, Wenming Yang, Zhongqian Sun, Xiaojuan Qi

Synthesizing realistic videos according to a given speech is still an open challenge. Previous works have been plagued by issues such as inaccurate lip shape generation and poor image quality. The key reason is that only motions and appearances on limited facial areas (e.g., lip area) are mainly driven by the input speech. Therefore, directly learning a mapping function from speech to the entire head image is prone to ambiguity, particularly when using a short video for training. We thus propose a decomposition-synthesis-composition framework named Speech to Lip (Speech2Lip) that disentangles speech-sensitive and speech-insensitive motion/appearance to facilitate effective learning from limited training data, resulting in the generation of natural-looking videos. First, given a fixed head pose (i.e., canonical space), we present a speech-driven implicit model for lip image generation which concentrates on learning speech-sensitive motion and appearance. Next, to model the major speech-insensitive motion (i.e., head movement), we introduce a geometry-aware mutual explicit mapping (GAMEM) module that establishes geometric mappings between different head poses. This allows us to paste generated lip images at the canonical space onto head images with arbitrary poses and synthesize talking videos with natural head movements. In addition, a Blend-Net and a contrastive sync loss are introduced to enhance the overall synthesis performance. Quantitative and qualitative results on three benchmarks demonstrate that our model can be trained by a video of just a few minutes in length and achieve state-of-the-art performance in both visual quality and speech-visual synchronization. Code: https://github.com/CVMI-Lab/Speech2Lip.

Sanjoy Chowdhury, Sreyan Ghosh, Subhrajyoti Dasgupta, Anton Ratnarajah, Utkarsh Tyagi, Dinesh Manocha

We present AdVerb, a novel audio-visual dereverberation framework that uses visual cues in addition to the reverberant sound to estimate clean audio. Although audio-only dereverberation is a well-studied problem, our approach incorporates the complementary visual modality to perform audio dereverberation. Given an image of the environment where the reverberated sound signal has been recorded, AdVerb employs a novel geometry-aware cross-modal transformer architecture that captures scene geometry and audio-visual cross-modal relationship to generate a complex ideal ratio mask, which, when applied to the reverberant audio predicts the clean sound. The effectiveness of our method is demonstrated through extensive quantitative and qualitative evaluations. Our approach significantly outperforms traditional audio-only and audio-visual baselines on three downstream tasks: speech enhancement, speech recognition, and speaker verification, with relative improvements in the range of 18% - 82% on the LibriSpeech test-clean set. We also achieve highly satisfactory RT60 error scores on the AVSpeech dataset.

Yasser Abdelaziz Dahou Djilali, Sanath Narayan, Haithem Boussaid, Ebtessam Almazrouei, Merouane Debbah

Visual Speech Recognition (VSR) differs from the common perception tasks as it requires deeper reasoning over the video sequence, even by human experts. Despite the recent advances in VSR, current approaches rely on labeled data to fully train or finetune their models predicting the target speech. This hinders their ability to generalize well beyond the training set and leads to performance degeneration under out-of-distribution challenging scenarios. Un-like previous works that involve auxiliary losses or com-plex training procedures and architectures, we propose a simple approach, named Lip2Vec that is based on learning a prior model. Given a robust visual speech encoder, this network maps the encoded latent representations of the lip sequence to their corresponding latents from the audio pair, which are sufficiently invariant for effective text decoding. The generated audio representation is then decoded to text using an off-the-shelf Audio Speech Recognition (ASR) model. The proposed model compares favorably with fully-supervised learning methods on the LRS3 dataset achieving 26 WER. Unlike SoTA approaches, our model keeps a rea-sonable performance on the VoxCeleb2-en test set. We believe that reprogramming the VSR as an ASR task narrows the performance gap between the two and paves the way for more flexible formulations of lip reading.

Shan He, Haonan He, Shuo Yang, Xiaoyan Wu, Pengcheng Xia, Bing Yin, Cong Liu, Lirong Dai, Chang Xu

Recent audio2mesh-based methods have shown promising prospects for speech-driven 3D facial animation tasks. However, some intractable challenges are urgent to be settled. For example, the data-scarcity problem is intrinsically inevitable due to the difficulty of 4D data collection. Besides, current methods generally lack controllability on the animated face. To this end, we propose a novel framework named Speech4Mesh to consecutively generate 4D talking head data and train the audio2mesh network with the reconstructed meshes. In our framework, we first reconstruct the 4D talking head sequence based on the monocular videos. For precise capture of the talking-related variation on the face, we exploit the audio-visual alignment information from the video by employing a contrastive learning scheme. We next can train the audio2mesh network (e.g., FaceFormer) based on the generated 4D data. To get control of the animated talking face, we encode the speaking-unrelated factors (e.g., emotion, etc.) into an emotion embedding for manipulation. Finally, a differentiable renderer guarantees more accurate photometric details of the reconstruction and animation results. Empirical experiments demonstrate that the Speech4Mesh framework can not only outperform state-of-the-art reconstruction methods, especially on the lower-face part but also achieve better animation performance both perceptually and objectively after pre-trained on the synthesized data. Besides, we also verify that the proposed framework is able to explicitly control the emotion of the animated talking face.

Zhe Niu, Brian Mak

Most lip-to-speech (LTS) synthesis models are trained and evaluated with the assumption that the audio-video pairs in the dataset are well synchronized. In this work, we demonstrate that commonly used audiovisual datasets such as GRID, TCD-TIMIT, and Lip2Wav can, however, have the data asynchrony issue, which will lead to inaccurate evaluation with conventional time alignment-sensitive metrics such as STOI, ESTOI, and MCD. Moreover, training an LTS model with such datasets can result in model asynchrony, meaning that the generated speech and input video are out of sync. To address these problems, we first provide a time-alignment frontend for the commonly used metrics to ensure accurate evaluation. Then, we propose a synchronized lip-to-speech (SLTS) model with an automatic synchronization mechanism (ASM) that corrects data asynchrony and penalizes model asynchrony during training. We evaluated the effectiveness of our approach on both artificial and popular audiovisual datasets. Our proposed method outperforms existing SOTA models in a variety of evaluation metrics.

Peiji Yang, Huawei Wei, Yicheng Zhong, Zhisheng Wang

Existing Speech-driven 3D facial animation methods typically follow the supervised paradigm, involving regression from speech to 3D facial animation. This paradigm faces two major challenges: the high cost of supervision acquisition, and the ambiguity in mapping between speech and lip movements. To address these challenges, this study proposes a novel cross-modal semi-supervised framework, comprising a Speech-to-Image Transcoder and a Face-to-Geometry Regressor. The former jointly learns a common representation space from speech and image domains, enabling the transformation of speech into semantically-consistent facial images. The latter is responsible for reconstructing 3D facial meshes from the transformed images. Both modules require minimal effort to acquire the necessary training data, thereby obviating the dependence on costly supervised data. Furthermore, the joint learning scheme enables the fusion of intricate visual features into speech encoding, thereby facilitating the transformation of subtle speech variations into nuanced lip movements, ultimately enhancing the fidelity of 3D face reconstructions. Consequently, the ambiguity of the direct mapping of speech-to-animation is significantly reduced, leading to coherent and high-fidelity generation of lip motion. Extensive experiments demonstrate that our approach produces competitive results compared to supervised methods.

Chaitanya Ahuja, Pratik Joshi, Ryo Ishii, Louis-Philippe Morency

Co-speech gestures are a key channel of human communication, making them important for personalized chat agents to generate. In the past, gesture generation models assumed that data for each speaker is available all at once, and in large amounts. However in practical scenarios, speaker data comes sequentially and in small amounts as the agent personalizes with more speakers, akin to a continual learning paradigm. While more recent works have shown progress in adapting to low-resource data, they catastrophically forget the gesture styles of initial speakers they were trained on. Also, prior generative continual learning works are not multimodal, making this space less studied. In this paper, we explore this new paradigm and propose C-DiffGAN: an approach that continually learns new speaker gesture styles with only a few minutes of per-speaker data, while retaining previously learnt styles. Inspired by prior continual learning works, C-DiffGAN encourages knowledge retention by 1) generating reminiscences of previous low-resource speaker data, then 2) crossmodally aligning to them to mitigate catastrophic forgetting. We quantitatively demonstrate improved performance and reduced forgetting over strong baselines through standard continual learning measures, reinforced by a qualitative user study that shows that our method produces more natural, style-preserving gestures. Code and videos can be found at https://chahuja.com/cdiffgan

Siddharth Gururani, Arun Mallya, Ting-Chun Wang, Rafael Valle, Ming-Yu Liu

Animating portraits using speech has received growing attention in recent years, with various creative and practical use cases. An ideal generated video should have good lip sync with the audio, natural facial expressions and head motions, and high frame quality. In this work, we present SPACE, which uses speech and a single image to generate high-resolution, and expressive videos with realistic head pose, without requiring a driving video. It uses a multi-stage approach, combining the controllability of facial landmarks with the high-quality synthesis power of a pretrained face generator. SPACE also allows for the control of emotions and their intensities. Our method outperforms prior methods in objective metrics for image quality and facial motions and is strongly preferred by users in pair-wise comparisons. Please visit the project page to view the videos and to see more results: https://research.nvidia.com/labs/dir/space.

Fangyun Wei, Yutong Chen

This work dedicates to continuous sign language recognition (CSLR), which is a weakly supervised task dealing with the recognition of continuous signs from videos, without any prior knowledge about the temporal boundaries between consecutive signs. Data scarcity heavily impedes the progress of CSLR. Existing approaches typically train CSLR models on a monolingual corpus, which is orders of magnitude smaller than that of speech recognition. In this work, we explore the feasibility of utilizing multilingual sign language corpora to facilitate monolingual CSLR. Our work is built upon the observation of cross-lingual signs, which originate from different sign languages but have similar visual signals (e.g., hand shape and motion). The underlying idea of our approach is to identify the cross-lingual signs in one sign language and properly leverage them as auxiliary training data to improve the recognition capability of another. To achieve the goal, we first build two sign language dictionaries containing isolated signs that appear in two datasets. Then we identify the sign-to-sign mappings between two sign languages via a well-optimized isolated sign language recognition model. At last, we train a CSLR model on the combination of the target data with original labels and the auxiliary data with mapped labels. Experimentally, our approach achieves state-of-the-art performance on two widely-used CSLR datasets: Phoenix-2014 and Phoenix-2014T.

Balamurugan Thambiraja, Ikhsanul Habibie, Sadegh Aliakbarian, Darren Cosker, Christian Theobalt, Justus Thies

Speech-driven 3D facial animation has been widely explored, with applications in gaming, character animation, virtual reality, and telepresence systems. State-of-the-art methods deform the face topology of the target actor to sync the input audio without considering the identity-specific speaking style and facial idiosyncrasies, thus, resulting in unrealistic and inaccurate lip movements. To address this, we present Imitator, a speech-driven facial expression synthesis method, which learns identity-specific details from a short input video and produces novel facial expressions matching the identity-specific speaking style and facial idiosyncrasies of the target actor. Specifically, we train a style-agnostic transformer on a large facial expression dataset which we use as a prior for audio-driven facial expressions. We utilize this prior to optimize for identity-specific speaking style based on a short reference video. To train the prior, we introduce a novel loss function based on detected bilabial consonants to ensure plausible lip closures and consequently improve the realism of the generated expressions. Through detailed experiments and user studies, we show that our approach improves Lip-Sync by 49% and produces expressive facial animations from input audio while preserving the actor's speaking style. Project page: https://balamuruganthambiraja.github.io/Imitator

Yihao Zhi, Xiaodong Cun, Xuelin Chen, Xi Shen, Wen Guo, Shaoli Huang, Shenghua Gao

Gestures are non-verbal but important behaviors accompanying people's speech. While previous methods are able to generate speech rhythm-synchronized gestures, the semantic context of the speech is generally lacking in the gesticulations. Although semantic gestures do not occur very regularly in human speech, they are indeed the key for the audience to understand the speech context in a more immersive environment. Hence, we introduce LivelySpeaker, a framework that realizes semantics-aware co-speech gesture generation and offers several control handles. Specifically, the script-based gesture generation leverages the pre-trained CLIP text embeddings as the guidance for generating gestures that are highly semantically aligned with the script. Then, we devise a simple but effective diffusion-based gesture generation backbone simply using pure MLPs, that is conditioned on only audio signals and learns to gesticulate with realistic motions. We utilize such powerful prior to rhyme the script-guided gestures with the audio signals, notably in a zero-shot setting. Our novel two-stage generation framework also enables several applications, such as changing the gesticulation style, editing the co-speech gestures via textual prompting, and controlling the semantic awareness and rhythm alignment with guided diffusion. Extensive experiments demonstrate the advantages of the proposed framework over competing methods. In addition, our core diffusion-based generative model also achieves state-of-the-art performance on two benchmarks. The code and model will be released to facilitate future research.