In this paper, we propose two novel approaches, which integrate long-content information into the factorized neural transducer (FNT) based architecture in both non-streaming (referred to as LongFNT ) and streaming (referred to as SLongFNT ) scenarios. We first investigate whether long-content transcriptions can improve the vanilla conformer transducer (C-T) models. Our experiments indicate that the vanilla C-T models do not exhibit improved performance when utilizing long-content transcriptions, possibly due to the predictor network of C-T models not functioning as a pure language model. Instead, FNT shows its potential in utilizing long-content information, where we propose the LongFNT model and explore the impact of long-content information in both text (LongFNT-Text) and speech (LongFNT-Speech). The proposed LongFNT-Text and LongFNT-Speech models further complement each other to achieve better performance, with transcription history proving more valuable to the model. The effectiveness of our LongFNT approach is evaluated on LibriSpeech and GigaSpeech corpora, and obtains relative 19% and 12% word error rate reduction, respectively. Furthermore, we extend the LongFNT model to the streaming scenario, which is named SLongFNT , consisting of SLongFNT-Text and SLongFNT-Speech approaches to utilize long-content text and speech information. Experiments show that the proposed SLongFNT model achieves relative 26% and 17% WER reduction on LibriSpeech and GigaSpeech respectively while keeping a good latency, compared to the FNT baseline. Overall, our proposed LongFNT and SLongFNT highlight the significance of considering long-content speech and transcription knowledge for improving both non-streaming and streaming speech recognition systems.
The linear classifier is widely used in various image classification tasks. It works by optimizing the distance between a sample and its corresponding class center. However, in real-world data, one class can contain several local clusters, e.g., birds of different poses. To address this complexity, we propose a novel multi-center classifier. Different from the vanilla linear classifier, our proposal is established on the assumption that the deep features of the training set follow a Gaussian Mixture distribution. Specifically, we create a conditional Gaussian distribution for each class and then sample multiple sub-centers from that distribution to extend the linear classifier. This approach allows the model to capture intra-class local structures more efficiently. In addition, at test time we set the mean of the conditional Gaussian distribution as the class center of the linear classifier and follow the vanilla linear classifier outputs, thus requiring no additional parameters or computational overhead. Extensive experiments on image classification show that the proposed multi-center classifier is a powerful alternative to widely used linear classifiers. Code available at https://github.com/ZheminZhang1/MultiCenter-Classifier.
Recently, Transformers have shown promising performance in various vision tasks. However, the high costs of global self-attention remain challenging for Transformers, especially for high-resolution vision tasks. Inspired by one of the most successful transformers-based models for NLP: Big Bird, we propose a novel sparse attention mechanism for Vision Transformers (ViT). Specifically, we separate the heads into three groups, the first group used convolutional neural network (CNN) to extract local features and provide positional information for the model, the second group used Random Sampling Windows (RS-Win) for sparse self-attention calculation, and the third group reduces the resolution of the keys and values by average pooling for global attention. Based on these components, ViT maintains the sparsity of self-attention while maintaining the merits of Big Bird (i.e., the model is a universal approximator of sequence functions and is Turing complete). Moreover, our results show that the positional encoding, a crucial component in ViTs, can be safely removed in our model. Experiments show that Vision Big Bird demonstrates competitive performance on common vision tasks.
Autonomous vehicle (AV) evaluation has been the subject of increased interest in recent years both in industry and in academia. This paper focuses on the development of a novel framework for generating adversarial driving behavior of background vehicle interfering against the AV to expose effective and rational risky events. Specifically, the adversarial behavior is learned by a reinforcement learning (RL) approach incorporated with the cumulative prospect theory (CPT) which allows representation of human risk cognition. Then, the extended version of deep deterministic policy gradient (DDPG) technique is proposed for training the adversarial policy while ensuring training stability as the CPT action-value function is leveraged. A comparative case study regarding the cut-in scenario is conducted on a high fidelity Hardware-in-the-Loop (HiL) platform and the results demonstrate the adversarial effectiveness to infer the weakness of the tested AV.
Due to the rapid development of computing hardware resources and the dramatic growth of data, pre-trained models in speech recognition, such as Whisper, have significantly improved the performance of speech recognition tasks. However, these models usually have a high computational overhead, making it difficult to execute effectively on resource-constrained devices. To speed up inference and reduce model size while maintaining performance, we propose a novel guided knowledge distillation and quantization for large pre-trained model Whisper. The student model selects distillation and quantization layers based on quantization loss and distillation loss, respectively. We compressed $\text{Whisper}_\text{small}$ to $\text{Whisper}_\text{base}$ and $\text{Whisper}_\text{tiny}$ levels, making $\text{Whisper}_\text{small}$ 5.18x/10.48x smaller, respectively. Moreover, compared to the original $\text{Whisper}_\text{base}$ and $\text{Whisper}_\text{tiny}$, there is also a relative character error rate~(CER) reduction of 11.3% and 14.0% for the new compressed model respectively.
Recently, Transformers have shown promising performance in various vision tasks. However, the high costs of global self-attention remain challenging for Transformers, especially for high-resolution vision tasks. Local self-attention runs attention computation within a limited region for the sake of efficiency, resulting in insufficient context modeling as their receptive fields are small. In this work, we introduce two new attention modules to enhance the global modeling capability of the hierarchical vision transformer, namely, random sampling windows (RS-Win) and important region windows (IR-Win). Specifically, RS-Win sample random image patches to compose the window, following a uniform distribution, i.e., the patches in RS-Win can come from any position in the image. IR-Win composes the window according to the weights of the image patches in the attention map. Notably, RS-Win is able to capture global information throughout the entire model, even in earlier, high-resolution stages. IR-Win enables the self-attention module to focus on important regions of the image and capture more informative features. Incorporated with these designs, RSIR-Win Transformer demonstrates competitive performance on common vision tasks.
Traditional automatic speech recognition~(ASR) systems usually focus on individual utterances, without considering long-form speech with useful historical information, which is more practical in real scenarios. Simply attending longer transcription history for a vanilla neural transducer model shows no much gain in our preliminary experiments, since the prediction network is not a pure language model. This motivates us to leverage the factorized neural transducer structure, containing a real language model, the vocabulary predictor. We propose the {LongFNT-Text} architecture, which fuses the sentence-level long-form features directly with the output of the vocabulary predictor and then embeds token-level long-form features inside the vocabulary predictor, with a pre-trained contextual encoder RoBERTa to further boost the performance. Moreover, we propose the {LongFNT} architecture by extending the long-form speech to the original speech input and achieve the best performance. The effectiveness of our LongFNT approach is validated on LibriSpeech and GigaSpeech corpora with 19% and 12% relative word error rate~(WER) reduction, respectively.
Face recognition has made tremendous progress in recent years due to the advances in loss functions and the explosive growth in training sets size. A properly designed loss is seen as key to extract discriminative features for classification. Several margin-based losses have been proposed as alternatives of softmax loss in face recognition. However, two issues remain to consider: 1) They overlook the importance of hard sample mining for discriminative learning. 2) Label noise ubiquitously exists in large-scale datasets, which can seriously damage the model's performance. In this paper, starting from the perspective of decision boundary, we propose a novel mining framework that focuses on the relationship between a sample's ground truth class center and its nearest negative class center. Specifically, a closed-set noise label self-correction module is put forward, making this framework work well on datasets containing a lot of label noise. The proposed method consistently outperforms SOTA methods in various face recognition benchmarks. Training code has been released at https://github.com/SWJTU-3DVision/BoundaryFace.
How to boost speech pre-training with textual data is an unsolved problem due to the fact that speech and text are very different modalities with distinct characteristics. In this paper, we propose a cross-modal Speech and Language Model (SpeechLM) to explicitly align speech and text pre-training with a pre-defined unified discrete representation. Specifically, we introduce two alternative discrete tokenizers to bridge the speech and text modalities, including phoneme-unit and hidden-unit tokenizers, which can be trained using a small amount of paired speech-text data. Based on the trained tokenizers, we convert the unlabeled speech and text data into tokens of phoneme units or hidden units. The pre-training objective is designed to unify the speech and the text into the same discrete semantic space with a unified Transformer network. Leveraging only 10K text sentences, our SpeechLM gets a 16\% relative WER reduction over the best base model performance (from 6.8 to 5.7) on the public LibriSpeech ASR benchmark. Moreover, SpeechLM with fewer parameters even outperforms previous SOTA models on CoVoST-2 speech translation tasks. We also evaluate our SpeechLM on various spoken language processing tasks under the universal representation evaluation framework SUPERB, demonstrating significant improvements on content-related tasks. Our code and models are available at https://aka.ms/SpeechLM.