Towards Rehearsal-Free Multilingual ASR: A LoRA-based Case Study on Whisper

Pre-trained multilingual speech foundation models, like Whisper, have shown impressive performance across different languages. However, adapting these models to new or specific languages is computationally extensive and faces catastrophic forgetting problems. Addressing these issues, our study investigates strategies to enhance the model on new languages in the absence of original training data, while also preserving the established performance on the original languages. Specifically, we first compare various LoRA-based methods to find out their vulnerability to forgetting. To mitigate this issue, we propose to leverage the LoRA parameters from the original model for approximate orthogonal gradient descent on the new samples. Additionally, we also introduce a learnable rank coefficient to allocate trainable parameters for more efficient training. Our experiments with a Chinese Whisper model (for Uyghur and Tibetan) yield better results with a more compact parameter set.

Task-Aware Dynamic Transformer for Efficient Arbitrary-Scale Image Super-Resolution

Arbitrary-scale super-resolution (ASSR) aims to learn a single model for image super-resolution at arbitrary magnifying scales. Existing ASSR networks typically comprise an off-the-shelf scale-agnostic feature extractor and an arbitrary scale upsampler. These feature extractors often use fixed network architectures to address different ASSR inference tasks, each of which is characterized by an input image and an upsampling scale. However, this overlooks the difficulty variance of super-resolution on different inference scenarios, where simple images or small SR scales could be resolved with less computational effort than difficult images or large SR scales. To tackle this difficulty variability, in this paper, we propose a Task-Aware Dynamic Transformer (TADT) as an input-adaptive feature extractor for efficient image ASSR. Our TADT consists of a multi-scale feature extraction backbone built upon groups of Multi-Scale Transformer Blocks (MSTBs) and a Task-Aware Routing Controller (TARC). The TARC predicts the inference paths within feature extraction backbone, specifically selecting MSTBs based on the input images and SR scales. The prediction of inference path is guided by a new loss function to trade-off the SR accuracy and efficiency. Experiments demonstrate that, when working with three popular arbitrary-scale upsamplers, our TADT achieves state-of-the-art ASSR performance when compared with mainstream feature extractors, but with relatively fewer computational costs. The code will be publicly released.

Unveiling the Potential of LLM-Based ASR on Chinese Open-Source Datasets

Large Language Models (LLMs) have demonstrated unparalleled effectiveness in various NLP tasks, and integrating LLMs with automatic speech recognition (ASR) is becoming a mainstream paradigm. Building upon this momentum, our research delves into an in-depth examination of this paradigm on a large open-source Chinese dataset. Specifically, our research aims to evaluate the impact of various configurations of speech encoders, LLMs, and projector modules in the context of the speech foundation encoder-LLM ASR paradigm. Furthermore, we introduce a three-stage training approach, expressly developed to enhance the model's ability to align auditory and textual information. The implementation of this approach, alongside the strategic integration of ASR components, enabled us to achieve the SOTA performance on the AISHELL-1, Test_Net, and Test_Meeting test sets. Our analysis presents an empirical foundation for future research in LLM-based ASR systems and offers insights into optimizing performance using Chinese datasets. We will publicly release all scripts used for data preparation, training, inference, and scoring, as well as pre-trained models and training logs to promote reproducible research.

Articulated Object Manipulation with Coarse-to-fine Affordance for Mitigating the Effect of Point Cloud Noise

3D articulated objects are inherently challenging for manipulation due to the varied geometries and intricate functionalities associated with articulated objects.Point-level affordance, which predicts the per-point actionable score and thus proposes the best point to interact with, has demonstrated excellent performance and generalization capabilities in articulated object manipulation. However, a significant challenge remains: while previous works use perfect point cloud generated in simulation, the models cannot directly apply to the noisy point cloud in the real-world. To tackle this challenge, we leverage the property of real-world scanned point cloud that, the point cloud becomes less noisy when the camera is closer to the object. Therefore, we propose a novel coarse-to-fine affordance learning pipeline to mitigate the effect of point cloud noise in two stages. In the first stage, we learn the affordance on the noisy far point cloud which includes the whole object to propose the approximated place to manipulate. Then, we move the camera in front of the approximated place, scan a less noisy point cloud containing precise local geometries for manipulation, and learn affordance on such point cloud to propose fine-grained final actions. The proposed method is thoroughly evaluated both using large-scale simulated noisy point clouds mimicking real-world scans, and in the real world scenarios, with superiority over existing methods, demonstrating the effectiveness in tackling the noisy real-world point cloud problem.

4K-Resolution Photo Exposure Correction at 125 FPS with ~8K Parameters

The illumination of improperly exposed photographs has been widely corrected using deep convolutional neural networks or Transformers. Despite with promising performance, these methods usually suffer from large parameter amounts and heavy computational FLOPs on high-resolution photographs. In this paper, we propose extremely light-weight (with only ~8K parameters) Multi-Scale Linear Transformation (MSLT) networks under the multi-layer perception architecture, which can process 4K-resolution sRGB images at 125 Frame-Per-Second (FPS) by a Titan RTX GPU. Specifically, the proposed MSLT networks first decompose an input image into high and low frequency layers by Laplacian pyramid techniques, and then sequentially correct different layers by pixel-adaptive linear transformation, which is implemented by efficient bilateral grid learning or 1x1 convolutions. Experiments on two benchmark datasets demonstrate the efficiency of our MSLTs against the state-of-the-arts on photo exposure correction. Extensive ablation studies validate the effectiveness of our contributions. The code is available at https://github.com/Zhou-Yijie/MSLTNet.

Spike-Triggered Contextual Biasing for End-to-End Mandarin Speech Recognition

The attention-based deep contextual biasing method has been demonstrated to effectively improve the recognition performance of end-to-end automatic speech recognition (ASR) systems on given contextual phrases. However, unlike shallow fusion methods that directly bias the posterior of the ASR model, deep biasing methods implicitly integrate contextual information, making it challenging to control the degree of bias. In this study, we introduce a spike-triggered deep biasing method that simultaneously supports both explicit and implicit bias. Moreover, both bias approaches exhibit significant improvements and can be cascaded with shallow fusion methods for better results. Furthermore, we propose a context sampling enhancement strategy and improve the contextual phrase filtering algorithm. Experiments on the public WenetSpeech Mandarin biased-word dataset show a 32.0% relative CER reduction compared to the baseline model, with an impressively 68.6% relative CER reduction on contextual phrases.

A First Order Meta Stackelberg Method for Robust Federated Learning

Previous research has shown that federated learning (FL) systems are exposed to an array of security risks. Despite the proposal of several defensive strategies, they tend to be non-adaptive and specific to certain types of attacks, rendering them ineffective against unpredictable or adaptive threats. This work models adversarial federated learning as a Bayesian Stackelberg Markov game (BSMG) to capture the defender's incomplete information of various attack types. We propose meta-Stackelberg learning (meta-SL), a provably efficient meta-learning algorithm, to solve the equilibrium strategy in BSMG, leading to an adaptable FL defense. We demonstrate that meta-SL converges to the first-order $\varepsilon$-equilibrium point in $O(\varepsilon^{-2})$ gradient iterations, with $O(\varepsilon^{-4})$ samples needed per iteration, matching the state of the art. Empirical evidence indicates that our meta-Stackelberg framework performs exceptionally well against potent model poisoning and backdoor attacks of an uncertain nature.

Lightweight Improved Residual Network for Efficient Inverse Tone Mapping

The display devices like HDR10 televisions are increasingly prevalent in our daily life for visualizing high dynamic range (HDR) images. But the majority of media images on the internet remain in 8-bit standard dynamic range (SDR) format. Therefore, converting SDR images to HDR ones by inverse tone mapping (ITM) is crucial to unlock the full potential of abundant media images. However, existing ITM methods are usually developed with complex network architectures requiring huge computational costs. In this paper, we propose a lightweight Improved Residual Network (IRNet) by enhancing the power of popular residual block for efficient ITM. Specifically, we propose a new Improved Residual Block (IRB) to extract and fuse multi-layer features for fine-grained HDR image reconstruction. Experiments on three benchmark datasets demonstrate that our IRNet achieves state-of-the-art performance on both the ITM and joint SR-ITM tasks. The code, models and data will be publicly available at https://github.com/ThisisVikki/ITM-baseline.

Emotional Talking Head Generation based on Memory-Sharing and Attention-Augmented Networks

Given an audio clip and a reference face image, the goal of the talking head generation is to generate a high-fidelity talking head video. Although some audio-driven methods of generating talking head videos have made some achievements in the past, most of them only focused on lip and audio synchronization and lack the ability to reproduce the facial expressions of the target person. To this end, we propose a talking head generation model consisting of a Memory-Sharing Emotion Feature extractor (MSEF) and an Attention-Augmented Translator based on U-net (AATU). Firstly, MSEF can extract implicit emotional auxiliary features from audio to estimate more accurate emotional face landmarks.~Secondly, AATU acts as a translator between the estimated landmarks and the photo-realistic video frames. Extensive qualitative and quantitative experiments have shown the superiority of the proposed method to the previous works. Codes will be made publicly available.

MAVD: The First Open Large-Scale Mandarin Audio-Visual Dataset with Depth Information

Audio-visual speech recognition (AVSR) gains increasing attention from researchers as an important part of human-computer interaction. However, the existing available Mandarin audio-visual datasets are limited and lack the depth information. To address this issue, this work establishes the MAVD, a new large-scale Mandarin multimodal corpus comprising 12,484 utterances spoken by 64 native Chinese speakers. To ensure the dataset covers diverse real-world scenarios, a pipeline for cleaning and filtering the raw text material has been developed to create a well-balanced reading material. In particular, the latest data acquisition device of Microsoft, Azure Kinect is used to capture depth information in addition to the traditional audio signals and RGB images during data acquisition. We also provide a baseline experiment, which could be used to evaluate the effectiveness of the dataset. The dataset and code will be released at https://github.com/SpringHuo/MAVD.