分享

In training speech recognition systems, labeling audio clips can be expensive, and not all data is equally valuable. Active learning aims to label only the most informative samples to reduce cost. For speech recognition, confidence scores and other likelihood-based active learning methods have been shown to be effective. Gradient-based active learning methods, however, are still not well-understood. This work investigates the Expected Gradient Length (EGL) approach in active learning for end-to-end speech recognition. We justify EGL from a variance reduction perspective, and observe that EGL's measure of informativeness picks novel samples uncorrelated with confidence scores. Experimentally, we show that EGL can reduce word errors by 11\%, or alternatively, reduce the number of samples to label by 50\%, when compared to random sampling.

In-context learning is a powerful capability of certain machine learning models that arguably underpins the success of today's frontier AI models. However, in-context learning is critically limited to settings where the in-context distribution of interest $p_{\theta}^{ICL}( x|\mathcal{D})$ can be straightforwardly expressed and/or parameterized by the model; for instance, language modeling relies on expressing the next-token distribution as a categorical distribution parameterized by the network's output logits. In this work, we present a more general form of in-context learning without such a limitation that we call \textit{in-context learning of energy functions}. The idea is to instead learn the unconstrained and arbitrary in-context energy function $E_{\theta}^{ICL}(x|\mathcal{D})$ corresponding to the in-context distribution $p_{\theta}^{ICL}(x|\mathcal{D})$. To do this, we use classic ideas from energy-based modeling. We provide preliminary evidence that our method empirically works on synthetic data. Interestingly, our work contributes (to the best of our knowledge) the first example of in-context learning where the input space and output space differ from one another, suggesting that in-context learning is a more-general capability than previously realized.

Recent strides in automatic speech recognition (ASR) have accelerated their application in the medical domain where their performance on accented medical named entities (NE) such as drug names, diagnoses, and lab results, is largely unknown. We rigorously evaluate multiple ASR models on a clinical English dataset of 93 African accents. Our analysis reveals that despite some models achieving low overall word error rates (WER), errors in clinical entities are higher, potentially posing substantial risks to patient safety. To empirically demonstrate this, we extract clinical entities from transcripts, develop a novel algorithm to align ASR predictions with these entities, and compute medical NE Recall, medical WER, and character error rate. Our results show that fine-tuning on accented clinical speech improves medical WER by a wide margin (25-34 % relative), improving their practical applicability in healthcare environments.

Self-Supervised Learning is vastly used to efficiently represent speech for Spoken Language Understanding, gradually replacing conventional approaches. Meanwhile, textual SSL models are proposed to encode language-agnostic semantics. SAMU-XLSR framework employed this semantic information to enrich multilingual speech representations. A recent study investigated SAMU-XLSR in-domain semantic enrichment by specializing it on downstream transcriptions, leading to state-of-the-art results on a challenging SLU task. This study's interest lies in the loss of multilingual performances and lack of specific-semantics training induced by such specialization in close languages without any SLU implication. We also consider SAMU-XLSR's loss of initial cross-lingual abilities due to a separate SLU fine-tuning. Therefore, this paper proposes a dual task learning approach to improve SAMU-XLSR semantic enrichment while considering distant languages for multilingual and language portability experiments.

Context. Risk analysis assesses potential risks in specific scenarios. Risk analysis principles are context-less; the same methodology can be applied to a risk connected to health and information technology security. Risk analysis requires a vast knowledge of national and international regulations and standards and is time and effort-intensive. A large language model can quickly summarize information in less time than a human and can be fine-tuned to specific tasks. Aim. Our empirical study aims to investigate the effectiveness of Retrieval-Augmented Generation and fine-tuned LLM in risk analysis. To our knowledge, no prior study has explored its capabilities in risk analysis. Method. We manually curated 193 unique scenarios leading to 1283 representative samples from over 50 mission-critical analyses archived by the industrial context team in the last five years. We compared the base GPT-3.5 and GPT-4 models versus their Retrieval-Augmented Generation and fine-tuned counterparts. We employ two human experts as competitors of the models and three other human experts to review the models and the former human experts' analysis. The reviewers analyzed 5,000 scenario analyses. Results and Conclusions. Human experts demonstrated higher accuracy, but LLMs are quicker and more actionable. Moreover, our findings show that RAG-assisted LLMs have the lowest hallucination rates, effectively uncovering hidden risks and complementing human expertise. Thus, the choice of model depends on specific needs, with FTMs for accuracy, RAG for hidden risks discovery, and base models for comprehensiveness and actionability. Therefore, experts can leverage LLMs as an effective complementing companion in risk analysis within a condensed timeframe. They can also save costs by averting unnecessary expenses associated with implementing unwarranted countermeasures.

Voice activity detection (VAD) is a critical component in various applications such as speech recognition, speech enhancement, and hands-free communication systems. With the increasing demand for personalized and context-aware technologies, the need for effective personalized VAD systems has become paramount. In this paper, we present a comparative analysis of Personalized Voice Activity Detection (PVAD) systems to assess their real-world effectiveness. We introduce a comprehensive approach to assess PVAD systems, incorporating various performance metrics such as frame-level and utterance-level error rates, detection latency and accuracy, alongside user-level analysis. Through extensive experimentation and evaluation, we provide a thorough understanding of the strengths and limitations of various PVAD variants. This paper advances the understanding of PVAD technology by offering insights into its efficacy and viability in practical applications using a comprehensive set of metrics.

A tensegrity-based system is a promising approach for dynamic exploration of uneven and unpredictable environments, particularly, space exploration. However, implementing such systems presents challenges in terms of intelligent aspects: state recognition, wireless monitoring, human interaction, and smart analyzing and advising function. Here, we introduce a 6-strut tensegrity integrate with 24 multimodal strain sensors by leveraging both deep learning model and large language models to realize smart tensegrity. Using conductive flexible tendons assisted by long short-term memory model, the tensegrity achieves the self-shape reconstruction without extern sensors. Through integrating the flask server and gpt-3.5-turbo model, the tensegrity autonomously enables to send data to iPhone for wireless monitoring and provides data analysis, explanation, prediction, and suggestions to human for decision making. Finally, human interaction system of the tensegrity helps human obtain necessary information of tensegrity from the aspect of human language. Overall, this intelligent tensegrity-based system with self-sensing tendons showcases potential for future exploration, making it a versatile tool for real-world applications.

Power dispatch is essential for providing stable, cost-effective, and eco-friendly electricity to society. However, traditional methods falter as power systems grow in scale and complexity, struggling with multitasking, swift problem-solving, and human-machine collaboration. This paper introduces GAIA, the pioneering Large Language Model (LLM) tailored for power dispatch tasks. We have developed a novel dataset construction technique that harnesses a range of data sources to fine-tune GAIA for optimal performance in this domain. This approach streamlines LLM training, allowing for the seamless integration of multidimensional data in power system management. Additionally, we have crafted specialized prompt strategies to boost GAIA's input-output efficiency in dispatch scenarios. When evaluated on the ElecBench benchmark, GAIA surpasses the baseline model LLaMA2 on multiple metrics. In practical applications, GAIA has demonstrated its ability to enhance decision-making processes, improve operational efficiency, and facilitate better human-machine interactions in power dispatch operations. This paper expands the application of LLMs to power dispatch and validates their practical utility, paving the way for future innovations in this field.

This paper introduces LLDif, a novel diffusion-based facial expression recognition (FER) framework tailored for extremely low-light (LL) environments. Images captured under such conditions often suffer from low brightness and significantly reduced contrast, presenting challenges to conventional methods. These challenges include poor image quality that can significantly reduce the accuracy of emotion recognition. LLDif addresses these issues with a novel two-stage training process that combines a Label-aware CLIP (LA-CLIP), an embedding prior network (PNET), and a transformer-based network adept at handling the noise of low-light images. The first stage involves LA-CLIP generating a joint embedding prior distribution (EPD) to guide the LLformer in label recovery. In the second stage, the diffusion model (DM) refines the EPD inference, ultilising the compactness of EPD for precise predictions. Experimental evaluations on various LL-FER datasets have shown that LLDif achieves competitive performance, underscoring its potential to enhance FER applications in challenging lighting conditions.

Non-blind rotary motion deblurring (RMD) aims to recover the latent clear image from a rotary motion blurred (RMB) image. The rotation center is a crucial input parameter in non-blind RMD methods. Existing methods directly estimate the rotation center from the RMB image. However they always suffer significant errors, and the performance of RMD is limited. For the assembled imaging systems, the position of the rotation center remains fixed. Leveraging this prior knowledge, we propose a geometric-based method for rotation center identification and analyze its error range. Furthermore, we construct a RMB imaging system. The experiment demonstrates that our method achieves less than 1-pixel error along a single axis (x-axis or y-axis). We utilize the constructed imaging system to capture real RMB images, and experimental results show that our method can help existing RMD approaches yield better RMD images.

Although the semantic communication with joint semantic-channel coding design has shown promising performance in transmitting data of different modalities over physical layer channels, the synchronization and packet-level forward error correction of multimodal semantics have not been well studied. Due to the independent design of semantic encoders, synchronizing multimodal features in both the semantic and time domains is a challenging problem. In this paper, we take the facial video and speech transmission as an example and propose a Synchronous Multimodal Semantic Communication System (SyncSC) with Packet-Level Coding. To achieve semantic and time synchronization, 3D Morphable Mode (3DMM) coefficients and text are transmitted as semantics, and we propose a semantic codec that achieves similar quality of reconstruction and synchronization with lower bandwidth, compared to traditional methods. To protect semantic packets under the erasure channel, we propose a packet-Level Forward Error Correction (FEC) method, called PacSC, that maintains a certain visual quality performance even at high packet loss rates. Particularly, for text packets, a text packet loss concealment module, called TextPC, based on Bidirectional Encoder Representations from Transformers (BERT) is proposed, which significantly improves the performance of traditional FEC methods. The simulation results show that our proposed SyncSC reduce transmission overhead and achieve high-quality synchronous transmission of video and speech over the packet loss network.

Diffusion models (DM) have become fundamental components of generative models, excelling across various domains such as image creation, audio generation, and complex data interpolation. Signal-to-Noise diffusion models constitute a diverse family covering most state-of-the-art diffusion models. While there have been several attempts to study Signal-to-Noise (S2N) diffusion models from various perspectives, there remains a need for a comprehensive study connecting different viewpoints and exploring new perspectives. In this study, we offer a comprehensive perspective on noise schedulers, examining their role through the lens of the signal-to-noise ratio (SNR) and its connections to information theory. Building upon this framework, we have developed a generalized backward equation to enhance the performance of the inference process.