This study proposes an acoustic sensing–based framework for driving environment recognition in electric vehicles (EVs), designed for intelligent transportation systems (ITS) in non-autonomous driving scenarios and edge-enabled Internet of Things (IoT) environments. The proposed approach analyzes short-duration acoustic signals and employs multiple feature representations, including MFCC, LFCC, and wavelet-based features. To address data scarcity and class imbalance, a feature-level generative adversarial network (GAN) is introduced for data augmentation. Experimental results demonstrate that MFCC-based features consistently achieve stable and superior recognition performance across different configurations. Moreover, GAN-based augmentation significantly improves recognition stability and accuracy for minority classes, such as tunnel and rainy conditions. In addition, under a unified experimental framework, this study systematically investigates the interactions among acoustic features, data augmentation strategies, and model architectures. The findings indicate that passive acoustic sensing offers advantages in terms of low cost and real-time computational capability, making it well suited for deployment in edge IoT systems. The proposed approach is applicable to intelligent transportation scenarios, including driver assistance and environmental perception for visually impaired passengers. Overall, the proposed approach offers advantages in terms of low cost, minimal privacy concerns, and real-time computational capability. It is well suited for deployment in edge computing environments and ITS applications, providing a practical solution for acoustic-based environmental perception in electric vehicles.

Neural network models for guitar amplifier emulation, while being effective, often demand high computational cost and lack interpretability. Drawing ideas from physical amplifier design, this paper aims to address these issues with a new differentiable digital signal processing (DDSP)-based model, called "DDSP guitar amp," that models the four components of a guitar amp (i.e., preamp, tone stack, power amp, and output transformer) using specific DSP-inspired designs. With a set of time- and frequency-domain metrics, we demonstrate that DDSP guitar amp achieves performance comparable with that of black-box baselines while requiring less than 10% of the computational operations per audio sample, thereby holding greater potential for usages in real-time applications.

In this paper, we propose a new dataset named EGDB, that contains transcriptions of the electric guitar performance of 240 tablatures rendered with different tones. Moreover, we benchmark the performance of two well-known transcription models proposed originally for the piano on this dataset, along with a multi-loss Transformer model that we newly propose. Our evaluation on this dataset and a separate set of real-world recordings demonstrate the influence of timbre on the accuracy of guitar sheet transcription, the potential of using multiple losses for Transformers, as well as the room for further improvement for this task.

In a recent paper, we have presented a generative adversarial network (GAN)-based model for unconditional generation of the mel-spectrograms of singing voices. As the generator of the model is designed to take a variable-length sequence of noise vectors as input, it can generate mel-spectrograms of variable length. However, our previous listening test shows that the quality of the generated audio leaves room for improvement. The present paper extends and expands that previous work in the following aspects. First, we employ a hierarchical architecture in the generator to induce some structure in the temporal dimension. Second, we introduce a cycle regularization mechanism to the generator to avoid mode collapse. Third, we evaluate the performance of the new model not only for generating singing voices, but also for generating speech voices. Evaluation result shows that new model outperforms the prior one both objectively and subjectively. We also employ the model to unconditionally generate sequences of piano and violin music and find the result promising. Audio examples, as well as the code for implementing our model, will be publicly available online upon paper publication.

We present in this paper PerformacnceNet, a neural network model we proposed recently to achieve score-to-audio music generation. The model learns to convert a music piece from the symbolic domain to the audio domain, assigning performance-level attributes such as changes in velocity automatically to the music and then synthesizing the audio. The model is therefore not just a neural audio synthesizer, but an AI performer that learns to interpret a musical score in its own way. The code and sample outputs of the model can be found online at https://github.com/bwang514/PerformanceNet.

In this paper, we introduce Dixit, an interactive visual storytelling system that the user interacts with iteratively to compose a short story for a photo sequence. The user initiates the process by uploading a sequence of photos. Dixit first extracts text terms from each photo which describe the objects (e.g., boy, bike) or actions (e.g., sleep) in the photo, and then allows the user to add new terms or remove existing terms. Dixit then generates a short story based on these terms. Behind the scenes, Dixit uses an LSTM-based model trained on image caption data and FrameNet to distill terms from each image, and utilizes a transformer decoder to compose a context-coherent story. Users change images or terms iteratively with Dixit to create the most ideal story. Dixit also allows users to manually edit and rate stories. The proposed procedure opens up possibilities for interpretable and controllable visual storytelling, allowing users to understand the story formation rationale and to intervene in the generation process.