Automated audio captioning (AAC) aims to generate informative descriptions for various sounds from nature and/or human activities. In recent years, AAC has quickly attracted research interest, with state-of-the-art systems now relying on a sequence-to-sequence (seq2seq) backbone powered by strong models such as Transformers. Following the macro-trend of applied machine learning research, in this work, we strive to improve the performance of seq2seq AAC models by extensively leveraging pretrained models and large language models (LLMs). Specifically, we utilize BEATs to extract fine-grained audio features. Then, we employ Instructor LLM to fetch text embeddings of captions, and infuse their language-modality knowledge into BEATs audio features via an auxiliary InfoNCE loss function. Moreover, we propose a novel data augmentation method that uses ChatGPT to produce caption mix-ups (i.e., grammatical and compact combinations of two captions) which, together with the corresponding audio mixtures, increase not only the amount but also the complexity and diversity of training data. During inference, we propose to employ nucleus sampling and a hybrid reranking algorithm, which has not been explored in AAC research. Combining our efforts, our model achieves a new state-of-the-art 32.6 SPIDEr-FL score on the Clotho evaluation split, and wins the 2023 DCASE AAC challenge.
相關內容
Recent achievements in language models have showcased their extraordinary capabilities in bridging visual information with semantic language understanding. This leads us to a novel question: can language models connect textual semantics with IoT sensory signals to perform recognition tasks, e.g., Human Activity Recognition (HAR)? If so, an intelligent HAR system with human-like cognition can be built, capable of adapting to new environments and unseen categories. This paper explores its feasibility with an innovative approach, IoT-sEnsors-language alignmEnt pre-Training (TENT), which jointly aligns textual embeddings with IoT sensor signals, including camera video, LiDAR, and mmWave. Through the IoT-language contrastive learning, we derive a unified semantic feature space that aligns multi-modal features with language embeddings, so that the IoT data corresponds to specific words that describe the IoT data. To enhance the connection between textual categories and their IoT data, we propose supplementary descriptions and learnable prompts that bring more semantic information into the joint feature space. TENT can not only recognize actions that have been seen but also ``guess'' the unseen action by the closest textual words from the feature space. We demonstrate TENT achieves state-of-the-art performance on zero-shot HAR tasks using different modalities, improving the best vision-language models by over 12%.
Simultaneous sequence generation is a pivotal task for real-time scenarios, such as streaming speech recognition, simultaneous machine translation and simultaneous speech translation, where the target sequence is generated while receiving the source sequence. The crux of achieving high-quality generation with low latency lies in identifying the optimal moments for generating, accomplished by learning a mapping between the source and target sequences. However, existing methods often rely on task-specific heuristics for different sequence types, limiting the model's capacity to adaptively learn the source-target mapping and hindering the exploration of multi-task learning for various simultaneous tasks. In this paper, we propose a unified segment-to-segment framework (Seg2Seg) for simultaneous sequence generation, which learns the mapping in an adaptive and unified manner. During the process of simultaneous generation, the model alternates between waiting for a source segment and generating a target segment, making the segment serve as the natural bridge between the source and target. To accomplish this, Seg2Seg introduces a latent segment as the pivot between source to target and explores all potential source-target mappings via the proposed expectation training, thereby learning the optimal moments for generating. Experiments on multiple simultaneous generation tasks demonstrate that Seg2Seg achieves state-of-the-art performance and exhibits better generality across various tasks.
The ethics of AI as both material and medium for interaction remains in murky waters within the context of musical and artistic practice. The interdisciplinarity of the field is revealing matters of concern and care, which necessitate interdisciplinary methodologies for evaluation to trouble and critique the inheritance of "residue-laden" AI-tools in musical applications. Seeking to unsettle these murky waters, this paper critically examines the example of Holly+, a deep neural network that generates raw audio in the likeness of its creator Holly Herndon. Drawing from theoretical concerns and considerations from speculative feminism and care ethics, we care-fully trouble the structures, frameworks and assumptions that oscillate within and around Holly+. We contribute with several considerations and contemplate future directions for integrating speculative feminism and care into musical-AI agent and system design, derived from our critical feminist examination.
Image quality assessment (IQA) plays a critical role in optimizing radiation dose and developing novel medical imaging techniques in computed tomography (CT). Traditional IQA methods relying on hand-crafted features have limitations in summarizing the subjective perceptual experience of image quality. Recent deep learning-based approaches have demonstrated strong modeling capabilities and potential for medical IQA, but challenges remain regarding model generalization and perceptual accuracy. In this work, we propose a multi-scale distributions regression approach to predict quality scores by constraining the output distribution, thereby improving model generalization. Furthermore, we design a dual-branch alignment network to enhance feature extraction capabilities. Additionally, semi-supervised learning is introduced by utilizing pseudo-labels for unlabeled data to guide model training. Extensive qualitative experiments demonstrate the effectiveness of our proposed method for advancing the state-of-the-art in deep learning-based medical IQA. Code is available at: //github.com/zunzhumu/MD-IQA.
Neural Machine Translation (NMT) has become a significant technology in natural language processing through extensive research and development. However, the deficiency of high-quality bilingual language pair data still poses a major challenge to improving NMT performance. Recent studies are exploring the use of contextual information from pre-trained language model (PLM) to address this problem. Yet, the issue of incompatibility between PLM and NMT model remains unresolved. This study proposes a PLM-integrated NMT (PiNMT) model to overcome the identified problems. The PiNMT model consists of three critical components, PLM Multi Layer Converter, Embedding Fusion, and Cosine Alignment, each playing a vital role in providing effective PLM information to NMT. Furthermore, two training strategies, Separate Learning Rates and Dual Step Training, are also introduced in this paper. By implementing the proposed PiNMT model and training strategy, we achieved state-of-the-art performance on the IWSLT'14 En$\leftrightarrow$De dataset. This study's outcomes are noteworthy as they demonstrate a novel approach for efficiently integrating PLM with NMT to overcome incompatibility and enhance performance.
Binaural stereo audio is recorded by imitating the way the human ear receives sound, which provides people with an immersive listening experience. Existing approaches leverage autoencoders and directly exploit visual spatial information to synthesize binaural stereo, resulting in a limited representation of visual guidance. For the first time, we propose a visually guided generative adversarial approach for generating binaural stereo audio from mono audio. Specifically, we develop a Stereo Audio Generation Model (SAGM), which utilizes shared spatio-temporal visual information to guide the generator and the discriminator to work separately. The shared visual information is updated alternately in the generative adversarial stage, allowing the generator and discriminator to deliver their respective guided knowledge while visually sharing. The proposed method learns bidirectional complementary visual information, which facilitates the expression of visual guidance in generation. In addition, spatial perception is a crucial attribute of binaural stereo audio, and thus the evaluation of stereo spatial perception is essential. However, previous metrics failed to measure the spatial perception of audio. To this end, a metric to measure the spatial perception of audio is proposed for the first time. The proposed metric is capable of measuring the magnitude and direction of spatial perception in the temporal dimension. Further, considering its function, it is feasible to utilize it instead of demanding user studies to some extent. The proposed method achieves state-of-the-art performance on 2 datasets and 5 evaluation metrics. Qualitative experiments and user studies demonstrate that the method generates space-realistic stereo audio.
Simultaneous Machine Translation (SiMT) aims to yield a real-time partial translation with a monotonically growing the source-side context. However, there is a counterintuitive phenomenon about the context usage between training and testing: e.g., the wait-k testing model consistently trained with wait-k is much worse than that model inconsistently trained with wait-k' (k' is not equal to k) in terms of translation quality. To this end, we first investigate the underlying reasons behind this phenomenon and uncover the following two factors: 1) the limited correlation between translation quality and training (cross-entropy) loss; 2) exposure bias between training and testing. Based on both reasons, we then propose an effective training approach called context consistency training accordingly, which makes consistent the context usage between training and testing by optimizing translation quality and latency as bi-objectives and exposing the predictions to the model during the training. The experiments on three language pairs demonstrate our intuition: our system encouraging context consistency outperforms that existing systems with context inconsistency for the first time, with the help of our context consistency training approach.
Research into methods for improving the performance of large language models (LLMs) through fine-tuning, retrieval-augmented generation (RAG) and soft-prompting has tended to focus on the use of highly technical or high-cost techniques, making many of the newly discovered approaches comparatively inaccessible to non-technical users. In this paper we tested an unmodified version of GPT 3.5, a fine-tuned version, and the same unmodified model when given access to a vectorised RAG database, both in isolation and in combination with a basic, non-algorithmic soft prompt. In each case we tested the model's ability to answer a set of 100 questions relating primarily to events that occurred after September 2021 (the point at which GPT 3.5's training data set ends). We found that if commercial platforms are used and default settings are applied with no iteration in order to establish a baseline set of outputs, a fine-tuned model outperforms GPT 3.5 Turbo, while the RAG approach out-performed both. The application of a soft prompt significantly improved the performance of each approach.
Video captioning is a challenging task that requires a deep understanding of visual scenes. State-of-the-art methods generate captions using either scene-level or object-level information but without explicitly modeling object interactions. Thus, they often fail to make visually grounded predictions, and are sensitive to spurious correlations. In this paper, we propose a novel spatio-temporal graph model for video captioning that exploits object interactions in space and time. Our model builds interpretable links and is able to provide explicit visual grounding. To avoid unstable performance caused by the variable number of objects, we further propose an object-aware knowledge distillation mechanism, in which local object information is used to regularize global scene features. We demonstrate the efficacy of our approach through extensive experiments on two benchmarks, showing our approach yields competitive performance with interpretable predictions.
Pre-trained deep neural network language models such as ELMo, GPT, BERT and XLNet have recently achieved state-of-the-art performance on a variety of language understanding tasks. However, their size makes them impractical for a number of scenarios, especially on mobile and edge devices. In particular, the input word embedding matrix accounts for a significant proportion of the model's memory footprint, due to the large input vocabulary and embedding dimensions. Knowledge distillation techniques have had success at compressing large neural network models, but they are ineffective at yielding student models with vocabularies different from the original teacher models. We introduce a novel knowledge distillation technique for training a student model with a significantly smaller vocabulary as well as lower embedding and hidden state dimensions. Specifically, we employ a dual-training mechanism that trains the teacher and student models simultaneously to obtain optimal word embeddings for the student vocabulary. We combine this approach with learning shared projection matrices that transfer layer-wise knowledge from the teacher model to the student model. Our method is able to compress the BERT_BASE model by more than 60x, with only a minor drop in downstream task metrics, resulting in a language model with a footprint of under 7MB. Experimental results also demonstrate higher compression efficiency and accuracy when compared with other state-of-the-art compression techniques.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191