NeurIPS 2024 Papers

We propose a novel approach for rendering high-quality spatial audio for 3D scenes that is in synchrony with the visual stream but does not rely or explicitly conditioned on the visual rendering. We demonstrate that such an approach enables the experience of immersive virtual tourism - performing a real-time dynamic navigation within the scene, experiencing both audio and visual content. Current audio-visual rendering approaches typically rely on visual cues, such as images, and thus visual artifacts could cause inconsistency in the audio quality. Furthermore, when such approaches are incorporated with visual rendering, audio generation at each viewpoint occurs after the rendering of the image of the viewpoint and thus could lead to audio lag that affects the integration of audio and visual streams. Our proposed approach, AV-Cloud, overcomes these challenges by learning the representation of the audio-visual scene based on a set of sparse AV anchor points, that constitute the Audio-Visual Cloud, and are derived from the camera calibration. The Audio-Visual Cloud serves as an audio-visual representation from which the generation of spatial audio for arbitrary listener location can be generated. In particular, we propose a novel module Audio-Visual Cloud Splatting which decodes AV anchor points into a spatial audio transfer function for the arbitrary viewpoint of the target listener. This function, applied through the Spatial Audio Render Head module, transforms monaural input into viewpoint-specific spatial audio. As a result, AV-Cloud efficiently renders the spatial audio aligned with any visual viewpoint and eliminates the need for pre-rendered images. We show that AV-Cloud surpasses current state-of-the-art accuracy on audio reconstruction, perceptive quality, and acoustic effects on two real-world datasets. AV-Cloud also outperforms previous methods when tested on scenes "in the wild".

In recent years, DeepFake technology has achieved unprecedented success in high-quality video synthesis, but these methods also pose potential and severe security threats to humanity. DeepFake can be bifurcated into entertainment applications like face swapping and illicit uses such as lip-syncing fraud. However, lip-forgery videos, which neither change identity nor have discernible visual artifacts, present a formidable challenge to existing DeepFake detection methods. Our preliminary experiments have shown that the effectiveness of the existing methods often drastically decrease or even fail when tackling lip-syncing videos. In this paper, for the first time, we propose a novel approach dedicated to lip-forgery identification that exploits the inconsistency between lip movements and audio signals. We also mimic human natural cognition by capturing subtle biological links between lips and head regions to boost accuracy. To better illustrate the effectiveness and advances of our proposed method, we create a high-quality LipSync dataset, AVLips, by employing the state-of-the-art lip generators. We hope this high-quality and diverse dataset could be well served the further research on this challenging and interesting field. Experimental results show that our approach gives an average accuracy of more than 95.3% in spotting lip-syncing videos, significantly outperforming the baselines. Extensive experiments demonstrate the capability to tackle deepfakes and the robustness in surviving diverse input transformations. Our method achieves an accuracy of up to 90.2% in real-world scenarios (e.g., WeChat video call) and shows its powerful capabilities in real scenario deployment. To facilitate the progress of this research community, we release all resources at https://github.com/AaronComo/LipFD.

Lip reading aims at transforming the videos of continuous lip movement into textual contents, and has achieved significant progress over the past decade. It serves as a critical yet practical assistance for speech-impaired individuals, with more practicability than speech recognition in noisy environments. With the increasing interpersonal communications in social media owing to globalization, the existing monolingual datasets for lip reading may not be sufficient to meet the exponential proliferation of bilingual and even multilingual users. However, to our best knowledge, research on code-switching is only explored in speech recognition, while the attempts in lip reading are seriously neglected. To bridge this gap, we have collected a bilingual code-switching lip reading benchmark composed of Chinese and English, dubbed CSLR. As the pioneering work, we recruited 62 speakers with proficient foundations in both spoken Chinese and English to express sentences containing both involved languages. Through rigorous criteria in data selection, CSLR benchmark has accumulated 85,560 video samples with a resolution of 1080x1920, totaling over 71.3 hours of high-quality code-switching lip movement data. To systematically evaluate the technical challenges in CSLR, we implement commonly-used lip reading backbones, as well as competitive solutions in code-switching speech for benchmark testing. Experiments show CSLR to be a challenging and under-explored lip reading task. We hope our proposed benchmark will extend the applicability of code-switching lip reading, and further contribute to the communities of cross-lingual communication and collaboration. Our dataset and benchmark are accessible at https://github.com/cslr-lipreading/CSLR.

Humans can picture a sound scene given an imprecise natural language description. For example, it is easy to imagine an acoustic environment given a phrase like "the lion roar came from right behind me!". For a machine to have the same degree of comprehension, the machine must know what a lion is (semantic attribute), what the concept of "behind" is (spatial attribute) and how these pieces of linguistic information align with the semantic and spatial attributes of the sound (what a roar sounds like when its coming from behind). State-of-the-art audio foundation models, such as CLAP, which learn to map between audio scenes and natural textual descriptions, are trained on non-spatial audio and text pairs, and hence lack spatial awareness. In contrast, sound event localization and detection models are limited to recognizing sounds from a fixed number of classes, and they localize the source to absolute position (e.g., 0.2m) rather than a position described using natural language (e.g., "next to me"). To address these gaps, we present ELSA (Embeddings for Language and Spatial Audio), a spatially aware-audio and text embedding model trained using multimodal contrastive learning. ELSA supports non-spatial audio, spatial audio, and open vocabulary text captions describing both the spatial and semantic components of sound. To train ELSA: (a) we spatially augment the audio and captions of three open-source audio datasets totaling 4,738 hours and 890,038 samples of audio comprised from 8,972 simulated spatial configurations, and (b) we design an encoder to capture the semantics of non-spatial audio, and the semantics and spatial attributes of spatial audio using contrastive learning. ELSA is a single model that is competitive with state-of-the-art for both semantic retrieval and 3D source localization. In particular, ELSA achieves +2.8\% mean audio-to-text and text-to-audio R@1 above the LAION-CLAP baseline, and outperforms by -11.6° mean-absolute-error in 3D source localization over the SeldNET baseline on the TUT Sound Events 2018 benchmark. Moreover, we show that the representation-space of ELSA is structured, enabling swapping of direction of audio via vector arithmetic of two directional text embeddings.

Respiratory audio, such as coughing and breathing sounds, has predictive power for a wide range of healthcare applications, yet is currently under-explored. The main problem for those applications arises from the difficulty in collecting large labeled task-specific data for model development. Generalizable respiratory acoustic foundation models pretrained with unlabeled data would offer appealing advantages and possibly unlock this impasse. However, given the safety-critical nature of healthcare applications, it is pivotal to also ensure openness and replicability for any proposed foundation model solution. To this end, we introduce OPERA, an OPEn Respiratory Acoustic foundation model pretraining and benchmarking system, as the first approach answering this need. We curate large-scale respiratory audio datasets ($\sim$136K samples, over 400 hours), pretrain three pioneering foundation models, and build a benchmark consisting of 19 downstream respiratory health tasks for evaluation. Our pretrained models demonstrate superior performance (against existing acoustic models pretrained with general audio on 16 out of 19 tasks) and generalizability (to unseen datasets and new respiratory audio modalities). This highlights the great promise of respiratory acoustic foundation models and encourages more studies using OPERA as an open resource to accelerate research on respiratory audio for health. The system is accessible from https://github.com/evelyn0414/OPERA.

Research in auditory, visual, and audiovisual speech recognition (ASR, VSR, and AVSR, respectively) has traditionally been conducted independently. Even recent self-supervised studies addressing two or all three tasks simultaneously tend to yield separate models, leading to disjoint inference pipelines with increased memory requirements and redundancies. This paper proposes unified training strategies for these systems. We demonstrate that training a single model for all three tasks enhances VSR and AVSR performance, overcoming typical optimisation challenges when training from scratch. Moreover, we introduce a greedy pseudo-labelling approach to more effectively leverage unlabelled samples, addressing shortcomings in related self-supervised methods. Finally, we develop a self-supervised pre-training method within our framework, proving its effectiveness alongside our semi-supervised approach. Despite using a single model for all tasks, our unified approach achieves state-of-the-art performance on LRS3 for ASR, VSR, and AVSR compared to recent methods. Code will be made publicly available.

Invasive brain-computer interfaces with Electrocorticography (ECoG) have shown promise for high-performance speech decoding in medical applications, but less damaging methods like intracranial stereo-electroencephalography (sEEG) remain underexplored. With rapid advances in representation learning, leveraging abundant recordings to enhance speech decoding is increasingly attractive. However, popular methods often pre-train temporal models based on brain-level tokens, overlooking that brain activities in different regions are highly desynchronized during tasks. Alternatively, they pre-train spatial-temporal models based on channel-level tokens but fail to evaluate them on challenging tasks like speech decoding, which requires intricate processing in specific language-related areas. To address this issue, we collected a well-annotated Chinese word-reading sEEG dataset targeting language-related brain networks from 12 subjects. Using this benchmark, we developed the Du-IN model, which extracts contextual embeddings based on region-level tokens through discrete codex-guided mask modeling. Our model achieves state-of-the-art performance on the 61-word classification task, surpassing all baselines. Model comparisons and ablation studies reveal that our design choices, including (\romannumeral1) temporal modeling based on region-level tokens by utilizing 1D depthwise convolution to fuse channels in the ventral sensorimotor cortex (vSMC) and superior temporal gyrus (STG) and (\romannumeral2) self-supervision through discrete codex-guided mask modeling, significantly contribute to this performance. Overall, our approach -- inspired by neuroscience findings and capitalizing on region-level representations from specific brain regions -- is suitable for invasive brain modeling and represents a promising neuro-inspired AI approach in brain-computer interfaces. Code and dataset are available at https://github.com/liulab-repository/Du-IN.

Audio-Visual Question Answering (AVQA) is a complex multi-modal reasoning task, demanding intelligent systems to accurately respond to natural language queries based on audio-video input pairs. Nevertheless, prevalent AVQA approaches are prone to overlearning dataset biases, resulting in poor robustness. Furthermore, current datasets may not provide a precise diagnostic for these methods. To tackle these challenges, firstly, we propose a novel dataset, *MUSIC-AVQA-R*, crafted in two steps: rephrasing questions within the test split of a public dataset (*MUSIC-AVQA*) and subsequently introducing distribution shifts to split questions. The former leads to a large, diverse test space, while the latter results in a comprehensive robustness evaluation on rare, frequent, and overall questions. Secondly, we propose a robust architecture that utilizes a multifaceted cycle collaborative debiasing strategy to overcome bias learning. Experimental results show that this architecture achieves state-of-the-art performance on MUSIC-AVQA-R, notably obtaining a significant improvement of 9.32\%. Extensive ablation experiments are conducted on the two datasets mentioned to analyze the component effectiveness within the debiasing strategy. Additionally, we highlight the limited robustness of existing multi-modal QA methods through the evaluation on our dataset. We also conduct experiments combining various baselines with our proposed strategy on two datasets to verify its plug-and-play capability. Our dataset and code are available at <https://github.com/reml-group/MUSIC-AVQA-R>.

Speech serves as a ubiquitous input interface for embedded mobile devices. Cloud-based solutions, while offering powerful speech understanding services, raise significant concerns regarding user privacy. To address this, disentanglement-based encoders have been proposed to remove sensitive information from speech signals without compromising the speech understanding functionality. However, these encoders demand high memory usage and computation complexity, making them impractical for resource-constrained wimpy devices. Our solution is based on a key observation that speech understanding hinges on long-term dependency knowledge of the entire utterance, in contrast to privacy-sensitive elements that are short-term dependent. Exploiting this observation, we propose SILENCE, a lightweight system that selectively obscuring short-term details, without damaging the long-term dependent speech understanding performance. The crucial part of SILENCE is a differential mask generator derived from interpretable learning to automatically configure the masking process. We have implemented SILENCE on the STM32H7 microcontroller and evaluate its efficacy under different attacking scenarios. Our results demonstrate that SILENCE offers speech understanding performance and privacy protection capacity comparable to existing encoders, while achieving up to 53.3$\times$ speedup and 134.1$\times$ reduction in memory footprint.

Understanding the behavioral and neural dynamics of social interactions is a goal of contemporary neuroscience. Many machine learning methods have emerged in recent years to make sense of complex video and neurophysiological data that result from these experiments. Less focus has been placed on understanding how animals process acoustic information, including social vocalizations. A critical step to bridge this gap is determining the senders and receivers of acoustic infor- mation in social interactions. While sound source localization (SSL) is a classic problem in signal processing, existing approaches are limited in their ability to localize animal-generated sounds in standard laboratory environments. Advances in deep learning methods for SSL are likely to help address these limitations, however there are currently no publicly available models, datasets, or benchmarks to systematically evaluate SSL algorithms in the domain of bioacoustics. Here, we present the VCL Benchmark: the first large-scale dataset for benchmarking SSL algorithms in rodents. We acquired synchronized video and multi-channel audio recordings of 767,295 sounds with annotated ground truth sources across 9 conditions. The dataset provides benchmarks which evaluate SSL performance on real data, simulated acoustic data, and a mixture of real and simulated data. We intend for this benchmark to facilitate knowledge transfer between the neuroscience and acoustic machine learning communities, which have had limited overlap.

The increasing realism of synthetic speech, driven by advancements in text-to-speech models, raises ethical concerns regarding impersonation and disinformation. Audio watermarking offers a promising solution via embedding human-imperceptible watermarks into AI-generated audios. However, the robustness of audio watermarking against common/adversarial perturbations remains understudied. We present AudioMarkBench, the first systematic benchmark for evaluating the robustness of audio watermarking against *watermark removal* and *watermark forgery*. AudioMarkBench includes a new dataset created from Common-Voice across languages, biological sexes, and ages, 3 state-of-the-art watermarking methods, and 15 types of perturbations. We benchmark the robustness of these methods against the perturbations in no-box, black-box, and white-box settings. Our findings highlight the vulnerabilities of current watermarking techniques and emphasize the need for more robust and fair audio watermarking solutions. Our dataset and code are publicly available at https://github.com/moyangkuo/AudioMarkBench.

Modern systems for automatic speech recognition, including the RNN-Transducer and Attention-based Encoder-Decoder (AED), are designed so that the encoder is not required to alter the time-position of information from the audio sequence into the embedding; alignment to the final text output is processed during decoding. We discover that the transformer-based encoder adopted in recent years is actually capable of performing the alignment internally during the forward pass, prior to decoding. This new phenomenon enables a simpler and more efficient model, the ''Aligner-Encoder''. To train it, we discard the dynamic programming of RNN-T in favor of the frame-wise cross-entropy loss of AED, while the decoder employs the lighter text-only recurrence of RNN-T without learned cross-attention---it simply scans embedding frames in order from the beginning, producing one token each until predicting the end-of-message. We conduct experiments demonstrating performance remarkably close to the state of the art, including a special inference configuration enabling long-form recognition. In a representative comparison, we measure the total inference time for our model to be 2x faster than RNN-T and 16x faster than AED. Lastly, we find that the audio-text alignment is clearly visible in the self-attention weights of a certain layer, which could be said to perform ''self-transduction''.

Consumer electronics used to follow the miniaturization trend described by Moore’s Law. Despite increased processing power in Microcontroller Units (MCUs), MCUs used in the smallest appliances are still not capable of running even moderately big, state-of-the-art artificial neural networks (ANNs) especially in time-sensitive scenarios. In this work, we present a novel method called Scattered Online Inference (SOI) that aims to reduce the computational complexity of ANNs. SOI leverages the continuity and seasonality of time-series data and model predictions, enabling extrapolation for processing speed improvements, particularly in deeper layers. By applying compression, SOI generates more general inner partial states of ANN, allowing skipping full model recalculation at each inference.

Workplace meetings are vital to organizational collaboration, yet a large percentage of meetings are rated as ineffective. To help improve meeting effectiveness by understanding if the conversation is on topic, we create a comprehensive Topic-Conversation Relevance (TCR) dataset that covers a variety of domains and meeting styles. The TCR dataset includes 1,500 unique meetings, 22 million words in transcripts, and over 15,000 meeting topics, sourced from both newly collected Speech Interruption Meeting (SIM) data and existing public datasets. Along with the text data, we also open source scripts to generate synthetic meetings or create augmented meetings from the TCR dataset to enhance data diversity. For each data source, benchmarks are created using GPT-4 to evaluate the model accuracy in understanding transcription-topic relevance.

Video-to-audio (V2A) generation aims to synthesize content-matching audio from silent video, and it remains challenging to build V2A models with high generation quality, efficiency, and visual-audio temporal synchrony. We propose Frieren, a V2A model based on rectified flow matching. Frieren regresses the conditional transport vector field from noise to spectrogram latent with straight paths and conducts sampling by solving ODE, outperforming autoregressive and score-based models in terms of audio quality. By employing a non-autoregressive vector field estimator based on a feed-forward transformer and channel-level cross-modal feature fusion with strong temporal alignment, our model generates audio that is highly synchronized with the input video. Furthermore, through reflow and one-step distillation with guided vector field, our model can generate decent audio in a few, or even only one sampling step. Experiments indicate that Frieren achieves state-of-the-art performance in both generation quality and temporal alignment on VGGSound, with alignment accuracy reaching 97.22\%, and 6.2\% improvement in inception score over the strong diffusion-based baseline. Audio samples and code are available at http://frieren-v2a.github.io.

The training of deep learning-based multichannel speech enhancement and source localization systems relies heavily on the simulation of room impulse response and multichannel diffuse noise, due to the lack of large-scale real-recorded datasets. However, the acoustic mismatch between simulated and real-world data could degrade the model performance when applying in real-world scenarios. To bridge this simulation-to-real gap, this paper presents a new relatively large-scale Real-recorded and annotated Microphone Array speech&Noise (RealMAN) dataset. The proposed dataset is valuable in two aspects: 1) benchmarking speech enhancement and localization algorithms in real scenarios; 2) offering a substantial amount of real-world training data for potentially improving the performance of real-world applications. Specifically, a 32-channel array with high-fidelity microphones is used for recording. A loudspeaker is used for playing source speech signals (about 35 hours of Mandarin speech). A total of 83.7 hours of speech signals (about 48.3 hours for static speaker and 35.4 hours for moving speaker) are recorded in 32 different scenes, and 144.5 hours of background noise are recorded in 31 different scenes. Both speech and noise recording scenes cover various common indoor, outdoor, semi-outdoor and transportation environments, which enables the training of general-purpose speech enhancement and source localization networks. To obtain the task-specific annotations, speaker location is annotated with an omni-directional fisheye camera by automatically detecting the loudspeaker. The direct-path signal is set as the target clean speech for speech enhancement, which is obtained by filtering the source speech signal with an estimated direct-path propagation filter. Baseline experiments demonstrate that i) compared to using simulated data, the proposed dataset is indeed able to train better speech enhancement and source localization networks; ii) using various sub-arrays of the proposed 32-channel microphone array can successfully train variable-array networks that can be directly used to unseen arrays.

We propose an unsupervised adaptation framework, Self-TAught Recognizer (STAR), which leverages unlabeled data to enhance the robustness of automatic speech recognition (ASR) systems in diverse target domains, such as noise and accents. STAR is developed for prevalent speech foundation models based on Transformer-related architecture with auto-regressive decoding (e.g., Whisper, Canary). Specifically, we propose a novel indicator that empirically integrates step-wise information during decoding to assess the token-level quality of pseudo labels without ground truth, thereby guiding model updates for effective unsupervised adaptation. Experimental results show that STAR achieves an average of 13.5% relative reduction in word error rate across 14 target domains, and it sometimes even approaches the upper-bound performance of supervised adaptation. Surprisingly, we also observe that STAR prevents the adapted model from the common catastrophic forgetting problem without recalling source-domain data. Furthermore, STAR exhibits high data efficiency that only requires less than one-hour unlabeled data, and seamless generality to alternative large speech models and speech translation tasks. Our code aims to open source to the research communities.

Interpreting the decisions of deep learning models, including audio classifiers, is crucial for ensuring the transparency and trustworthiness of this technology. In this paper, we introduce LMAC-ZS (Listenable Maps for Zero-Shot Audio Classifiers), which, to the best of our knowledge, is the first decoder-based post-hoc explanation method for explaining the decisions of zero-shot audio classifiers. The proposed method utilizes a novel loss function that aims to closely reproduce the original similarity patterns between text-and-audio pairs in the generated explanations. We provide an extensive evaluation using the Contrastive Language-Audio Pretraining (CLAP) model to showcase that our interpreter remains faithful to the decisions in a zero-shot classification context. Moreover, we qualitatively show that our method produces meaningful explanations that correlate well with different text prompts.

The content of visual and audio scenes is multi-faceted such that a video stream can be paired with various audio streams and vice-versa. Thereby, in video-to-audio generation task, it is imperative to introduce steering approaches for controlling the generated audio. While Video-to-Audio generation is a well-established generative task, existing methods lack such controllability. In this work, we propose VATT, a multi-modal generative framework that takes a video and an optional text prompt as input, and generates audio and optional textual description (caption) of the audio. Such a framework has two unique advantages: i) Video-to-Audio generation process can be refined and controlled via text which complements the context of the visual information, and ii) The model can suggest what audio to generate for the video by generating audio captions. VATT consists of two key modules: VATT Converter, which is an LLM that has been fine-tuned for instructions and includes a projection layer that maps video features to the LLM vector space, and VATT Audio, a bi-directional transformer that generates audio tokens from visual frames and from optional text prompt using iterative parallel decoding. The audio tokens and the text prompt are used by a pretrained neural codec to convert them into a waveform. Our experiments show that when VATT is compared to existing video-to-audio generation methods in objective metrics, such as VGGSound audiovisual dataset, it achieves competitive performance when the audio caption is not provided. When the audio caption is provided as a prompt, VATT achieves even more refined performance (with lowest KLD score of 1.41). Furthermore, subjective studies asking participants to choose the most compatible generated audio for a given silent video, show that VATT Audio has been chosen on average as a preferred generated audio than the audio generated by existing methods. VATT enables controllable video-to-audio generation through text as well as suggesting text prompts for videos through audio captions, unlocking novel applications such as text-guided video-to-audio generation and video-to-audio captioning.