Search

For many Automatic Speech Recognition (ASR) tasks audio features as spectrograms show better results than Mel-frequency Cepstral Coefficients (MFCC), but in practice they are hard to use due to a complex dimensionality of a feature space. The following paper presents an alternative approach towards generating compressed spectrogram representation, based on Convolutional Variational Autoencoders (VAE). A Convolutional VAE model was trained on a subsample of the LibriSpeech dataset to reconstruct short fragments of audio spectrograms (25 ms) from a 13-dimensional embedding. The trained model for a 40-dimensional (300 ms) embedding was used to generate features for corpus of spoken commands on the GoogleSpeechCommands dataset. Using the generated features an ASR system was built and compared to the model with MFCC features., Comment: Theory and Practice of Natural Computing 9th International Conference, TPNC 2020, Taoyuan, Taiwan, 2020, Proceedings 9

We present a novel method for predicting binary phase diagrams through the automatic construction of a minimal basis set of representative templates. The core assumption is that any materials space can be divided into a small number of regions with similar chemical tendencies and bonding properties, and that a minimal set of templates can efficiently represent the key chemical trends across the different regions. By combining data-driven techniques with ab-initio crystal structure prediction, we can efficiently partition the materials space and construct templates reflecting variations in chemical behavior. Preliminary results demonstrate that our method predicts binary convex hulls with accuracy comparable to resource-intensive EA searches, while achieving a significant reduction in computational time (by a factor of 25). The method can be extended to ternary and multinary systems, enabling efficient high-throughput exploration and mapping of complex material spaces. By providing a transformative solution for high-throughput materials discovery, our approach paves the way for uncovering advanced quantum materials and accelerating in silico design., Comment: 5 figures, 2 tables, 11 pages

Soil sinkholes significantly influence soil degradation, but their irregular shapes, along with interference from shadow and vegetation, make it challenging to accurately quantify their properties using remotely sensed data. We present a novel framework for sinkhole segmentation that combines traditional topographic computations of closed depressions with the newly developed prompt-based Segment Anything Model (SAM). Within this framework, termed SinkSAM, we highlight four key improvements: (1) The integration of topographic computations with SAM enables pixel-level refinement of sinkhole boundaries segmentation; (2) A coherent mathematical prompting strategy, based on closed depressions, addresses the limitations of purely learning-based models (CNNs) in detecting and segmenting undefined sinkhole features, while improving generalization to new, unseen regions; (3) Using Depth Anything V2 monocular depth for automatic prompts eliminates photogrammetric biases, enabling sinkhole mapping without the dependence on LiDAR data; and (4) An established sinkhole database facilitates fine-tuning of SAM, improving its zero-shot performance in sinkhole segmentation. These advancements allow the deployment of SinkSAM, in an unseen test area, in the highly variable semiarid region, achieving an intersection-over-union (IoU) of 40.27\% and surpassing previous results. This paper also presents the first SAM implementation for sinkhole segmentation and demonstrates the robustness of SinkSAM in extracting sinkhole maps using a single RGB image., Comment: 14 pages, 14 figures

Open-ended short-answer questions (SAGs) have been widely recognized as a powerful tool for providing deeper insights into learners' responses in the context of learning analytics (LA). However, SAGs often present challenges in practice due to the high grading workload and concerns about inconsistent assessments. With recent advancements in natural language processing (NLP), automatic short-answer grading (ASAG) offers a promising solution to these challenges. Despite this, current ASAG algorithms are often limited in generalizability and tend to be tailored to specific questions. In this paper, we propose a unified multi-agent ASAG framework, GradeOpt, which leverages large language models (LLMs) as graders for SAGs. More importantly, GradeOpt incorporates two additional LLM-based agents - the reflector and the refiner - into the multi-agent system. This enables GradeOpt to automatically optimize the original grading guidelines by performing self-reflection on its errors. Through experiments on a challenging ASAG task, namely the grading of pedagogical content knowledge (PCK) and content knowledge (CK) questions, GradeOpt demonstrates superior performance in grading accuracy and behavior alignment with human graders compared to representative baselines. Finally, comprehensive ablation studies confirm the effectiveness of the individual components designed in GradeOpt.

Endoscopy is a crucial tool for diagnosing the gastrointestinal tract, but its effectiveness is often limited by a narrow field of view and the dynamic nature of the internal environment, especially in the esophagus, where complex and repetitive patterns make image stitching challenging. This paper introduces a novel automatic image unfolding and stitching framework tailored for esophageal videos captured during endoscopy. The method combines feature matching algorithms, including LoFTR, SIFT, and ORB, to create a feature filtering pool and employs a Density-Weighted Homography Optimization (DWHO) algorithm to enhance stitching accuracy. By merging consecutive frames, the framework generates a detailed panoramic view of the esophagus, enabling thorough and accurate visual analysis. Experimental results show the framework achieves low Root Mean Square Error (RMSE) and high Structural Similarity Index (SSIM) across extensive video sequences, demonstrating its potential for clinical use and improving the quality and continuity of endoscopic visual data.

We present a cost-effective approach for developing Automatic Speech Recognition (ASR) models for low-resource languages like Ika. We fine-tune the pretrained wav2vec 2.0 Massively Multilingual Speech Models on a high-quality speech dataset compiled from New Testament Bible translations in Ika. Our results show that fine-tuning multilingual pretrained models achieves a Word Error Rate (WER) of 0.5377 and Character Error Rate (CER) of 0.2651 with just over 1 hour of training data. The larger 1 billion parameter model outperforms the smaller 300 million parameter model due to its greater complexity and ability to store richer speech representations. However, we observe overfitting to the small training dataset, reducing generalizability. Our findings demonstrate the potential of leveraging multilingual pretrained models for low-resource languages. Future work should focus on expanding the dataset and exploring techniques to mitigate overfitting., Comment: 10 pages, 5 Figures This is a pre-release version

There have been several studies on automatically generating piano covers, and recent advancements in deep learning have enabled the creation of more sophisticated covers. However, existing automatic piano cover models still have room for improvement in terms of expressiveness and fidelity to the original. To address these issues, we propose a learning algorithm called AMT-APC, which leverages the capabilities of automatic music transcription models. By utilizing the strengths of well-established automatic music transcription models, we aim to improve the accuracy of piano cover generation. Our experiments demonstrate that the AMT-APC model reproduces original tracks more accurately than any existing models.

Final written examination is the most important part of summative assessment in automatic control courses. Preparation of the examinations with a given number of points according to the concept of Constructive Alignment (which could be the main concept in future automatic control education) takes significant amount of time of the educator and motivates development of a toolkit for automatic compilation of examination problems. A decision support Matlab-LATEX toolkit based on random number generators for selection of examination problems is described in this report to facilitate the alignment. The toolkit allows application of Stepwise Constructive Alignment (a new method described in this report), where the alignment is achieved by a number of software runs associated with random trials. In each step the educator manually selects suitable problems before each run based on evaluation of the random choice from the previous run. Automatic generation of the examination together with solutions for the course 'Process control and measurement techniques' is presented as an example.

Stakeholders' conversations in requirements elicitation meetings contain valuable information, but manually extracting system requirements from these discussions is a time-consuming and labor-intensive task, and there is a risk of errors and the introduction of biases. While current methods assist in summarizing conversations and classifying requirements based on their nature, there is a noticeable lack of approaches capable of both identifying requirements within these conversations and generating corresponding system requirements. These approaches would significantly reduce the burden on requirements engineers, reducing the time and effort required. They would also support the production of accurate and consistent requirements documentation. To address this gap, this paper introduces RECOVER (Requirements EliCitation frOm conVERsations), a novel requirements engineering approach that leverages NLP and foundation models to automatically extract system requirements from stakeholder interactions. The approach is evaluated using a mixed-method research design that combines statistical performance analysis with a user study involving requirements engineers. First, at the conversation turn level, the evaluation measures RECOVER's accuracy in identifying requirements-relevant dialogue and the quality of generated requirements in terms of correctness, completeness, and actionability. Second, at the entire conversation level, the evaluation assesses the overall usefulness and effectiveness of RECOVER in synthesizing comprehensive system requirements from full stakeholder discussions. The evaluation shows promising results regarding the performance of RECOVER, as the generated requirements exhibit satisfactory quality in their correctness, completeness, and actionability. Moreover, the results show the potential usefulness of automating the process of eliciting requirements from conversation.

Function as a Service (FaaS) is poised to become the foundation of the next generation of cloud systems due to its inherent advantages in scalability, cost-efficiency, and ease of use. However, challenges such as the need for specialized knowledge and difficulties in building function workflows persist for cloud-native application developers. To overcome these challenges and mitigate the burden of developing FaaS-based applications, in this paper, we propose a mechanism called Action Engine, that makes use of Tool-Augmented Large Language Models (LLMs) at its kernel to interpret human language queries and automates FaaS workflow generation, thereby, reducing the need for specialized expertise and manual design. Action Engine includes modules to identify relevant functions from the FaaS repository and seamlessly manage the data dependency between them, ensuring that the developer's query is processed and resolved. Beyond that, Action Engine can execute the generated workflow by feeding the user-provided parameters. Our evaluations show that Action Engine can generate workflows with up to 20\% higher correctness without developer involvement. We notice that Action Engine can unlock FaaS workflow generation for non-cloud-savvy developers and expedite the development cycles of cloud-native applications., Comment: Accepted at Utility Cloud Computing (UCC '24) conference

The expanding influence of social media platforms over the past decade has impacted the way people communicate. The level of obscurity provided by social media and easy accessibility of the internet has facilitated the spread of hate speech. The terms and expressions related to hate speech gets updated with changing times which poses an obstacle to policy-makers and researchers in case of hate speech identification. With growing number of individuals using their native languages to communicate with each other, hate speech in these low-resource languages are also growing. Although, there is awareness about the English-related approaches, much attention have not been provided to these low-resource languages due to lack of datasets and online available data. This article provides a detailed survey of hate speech detection in low-resource languages around the world with details of available datasets, features utilized and techniques used. This survey further discusses the prevailing surveys, overlapping concepts related to hate speech, research challenges and opportunities., Comment: 34 pages, 12 figures

Identifying defects and anomalies in industrial products is a critical quality control task. Traditional manual inspection methods are slow, subjective, and error-prone. In this work, we propose a novel zero-shot training-free approach for automated industrial image anomaly detection using a multimodal machine learning pipeline, consisting of three foundation models. Our method first uses a large language model, i.e., GPT-3. generate text prompts describing the expected appearances of normal and abnormal products. We then use a grounding object detection model, called Grounding DINO, to locate the product in the image. Finally, we compare the cropped product image patches to the generated prompts using a zero-shot image-text matching model, called CLIP, to identify any anomalies. Our experiments on two datasets of industrial product images, namely MVTec-AD and VisA, demonstrate the effectiveness of this method, achieving high accuracy in detecting various types of defects and anomalies without the need for model training. Our proposed model enables efficient, scalable, and objective quality control in industrial manufacturing settings., Comment: Accepted to APSIPA ASC 2024

Self-supervised learning (SSL) models have shown exceptional capabilities across various speech-processing tasks. Continuous SSL representations are effective but suffer from high computational and storage demands. On the other hand, discrete SSL representations, although with degraded performance, reduce transmission and storage costs, and improve input sequence efficiency through de-duplication and subword-modeling. To boost the performance of discrete representations for ASR, we introduce a novel fusion mechanism that integrates two discrete representations. The fusion mechanism preserves all the benefits of discrete representation while enhancing the model's performance by integrating complementary information. Additionally, we explore "self-augmented'' discrete representations, which apply transformations to a single continuous SSL representation, eliminating the fusion mechanism's dependency on multiple SSL models and further decreasing its inference costs. Experimental results on benchmarks, including LibriSpeech and ML-SUPERB, indicate up to 19% and 24% relative character error rate improvement compared with the non-fusion baseline, validating the effectiveness of our proposed methods., Comment: SLT 2024