This study investigates the application of adaptive beamforming techniques within D-band sub-terahertz (sub-THz) communication systems tailored for 6G applications. We present a hardware-in-the-loop transmission system utilizing newly developed prototypes of transmit and receive front ends operating in the frequency range from 150 to 170 GHz. The front ends’ analog beamforming architecture enables the generation of eight distinct beams with 6° separation in azimuth, thus creating a field of view with 48° one dimensional angular scanning range on either side of the link. The system implements dynamic beamforming based on the 5G New Radio (NR) waveform’s design principles for the initial access/beam acquisition procedure. Experimental performance assessments conducted in an indoor environment prove the system’s potential to support mobility and mitigate the effects of signal blockage. Specifically, when encountering a lineof-sight link blockage event, the system successfully transitioned to a reflected propagation path, incurring approximately 4dB of loss. Additionally, a mobile receiver could be tracked while maintaining a 1dB variation in the wireless link budget. These results demonstrate the feasibility of D-band adaptive beamforming.

This paper reports the development outcomes of the world's first integrated analog beamforming - transmit and receive - wireless front-ends operating in the D-band (a sub-THz band), particularly designed to operate within 150 GHz to 170 GHz frequency range. Front-end hardware development includes monolithic microwave integrated circuit (MMIC) chips of the multichannel power amplifier, multichannel low-noise amplifier, and RF switches. Moreover, the development includes an analog beamforming RF network and a low-profile microstrip 1-by-8 uniform linear antenna array, which were both developed on a resistive silicon substrate. The paper also features a successful long-range (320-meter) line-of-sight unidirectional point-to-point wireless transmission experiment, utilizing a 5G-NR orthogonal frequency division multiplexing (OFDM) waveform over a 160-GHz carrier frequency. The experiment demonstrated a successful transmission of OFDM waveforms using up to a 16-QAM (quadrature amplitude modulation) scheme in the D-band.

This paper introduces an efficient model training method for anomaly detection of radio units (RUs) in 5G cellular networks. The proposed method uses Bayesian neural network (BNN)-based models that are selectively trained to reduce computing resources required for the model updating. In particular, an interquartile range (IQR)-based outlier detection of the uncertainty data from the BNN model is used for the selective learning. Our simulation results show that the resource required for model retraining is reduced by about 40%, and the reliability of the model improved by 1.5~7.9%. We expect that the proposed method can contribute to a more cost-effective and reliable anomaly monitoring in 5G Network.

Lack of large-scale note-level labeled data is the major obstacle to singing transcription from polyphonic music. We address the issue by using pseudo labels from vocal pitch estimation models given unlabeled data. The proposed method first converts the frame-level pseudo labels to note-level through pitch and rhythm quantization steps. Then, it further improves the label quality through self-training in a teacher-student framework. To validate the method, we conduct various experiment settings by investigating two vocal pitch estimation models as pseudo-label generators, two setups of teacher-student frameworks, and the number of iterations in self-training. The results show that the proposed method can effectively leverage large-scale unlabeled audio data and self-training with the noisy student model helps to improve performance. Finally, we show that the model trained with only unlabeled data has comparable performance to previous works and the model trained with additional labeled data achieves higher accuracy than the model trained with only labeled data.

As process technologies are scaled down, interconnect delay becomes major component of entire path delay, and vias represent a significant portion of the interconnect delay. In this paper, a novel variation-aware delay computation method for vias is proposed. Our experiments show that this method can reduce over five percent of pessimism in arrival time calculation when it is compared with state-of-the-art solutions.

Music similarity search is useful for a variety of creative tasks such as replacing one music recording with another recording with a similar "feel", a common task in video editing. For this task, it is typically necessary to define a similarity metric to compare one recording to another. Music similarity, however, is hard to define and depends on multiple simultaneous notions of similarity (i.e. genre, mood, instrument, tempo). While prior work ignore this issue, we embrace this idea and introduce the concept of multidimensional similarity and unify both global and specialized similarity metrics into a single, semantically disentangled multidimensional similarity metric. To do so, we adapt a variant of deep metric learning called conditional similarity networks to the audio domain and extend it using track-based information to control the specificity of our model. We evaluate our method and show that our single, multidimensional model outperforms both specialized similarity spaces and alternative baselines. We also run a user-study and show that our approach is favored by human annotators as well.

Singing voice is a key sound source in popular music. As recent music streaming and entertainment services call for more intelligent solutions to retrieve songs or evaluate musical characteristics, automatic analysis of popular music targeted to singing voice has been a significant research subject. The majority of studies have focused on quantitative or objective information of singing voice such as pitch, lyrics or singer identity. However, singing voice has a wide variety of dimensions that are somewhat difficult to quantify and therefore we often describe by words. In this article, we address the qualitative analysis of singing voice as a music auto-tagging task that annotates songs with a set of tag words. To this end, we build a music tag dataset dedicated to singing voice. Specifically, we define a vocabulary that describes timbre and singing styles of K-pop vocalists and collect human annotations for individual tracks. We then conduct statistical analysis to understand the global and temporal characteristics of the tag words. Using the dataset, we train a deep neural network model to automatically predict the voice-specific tags from popular music recordings and evaluate the model in different conditions. We discuss the results by comparing them to the statistical analysis of tag words. Finally, we show potential applications of the vocal tagging system in music retrieval, music thumbnailing and singing evaluation.

Recent work has shown that the end-to-end approach using convolutional neural network (CNN) is effective in various types of machine learning tasks. For audio signals, the approach takes raw waveforms as input using an 1-D convolution layer. In this paper, we improve the 1-D CNN architecture for music auto-tagging by adopting building blocks from state-of-the-art image classification models, ResNets and SENets, and adding multi-level feature aggregation to it. We compare different combinations of the modules in building CNN architectures. The results show that they achieve significant improvements over previous state-of-the-art models on the MagnaTagATune dataset and comparable results on Million Song Dataset. Furthermore, we analyze and visualize our model to show how the 1-D CNN operates.

Music auto-tagging is often handled in a similar manner to image classification by regarding the two-dimensional audio spectrogram as image data. However, music auto-tagging is distinguished from image classification in that the tags are highly diverse and have different levels of abstraction. Considering this issue, we propose a convolutional neural networks (CNN)-based architecture that embraces multi-level and multi-scaled features. The architecture is trained in three steps. First, we conduct supervised feature learning to capture local audio features using a set of CNNs with different input sizes. Second, we extract audio features from each layer of the pretrained convolutional networks separately and aggregate them altogether giving a long audio clip. Finally, we put them into fully connected networks and make final predictions of the tags. Our experiments show that using the combination of multi-level and multi-scale features is highly effective in music auto-tagging and the proposed method outperforms the previous state-of-the-art methods on the MagnaTagATune dataset and the Million Song Dataset. We further show that the proposed architecture is useful in transfer learning.

As combinations of signoff corners grow in modern SoCs, minimization of clock skew variation across corners is important. Large skew variation can cause difficulties in multi-corner timing closure because fixing violations at one corner can lead to violations at other corners. Such "ping-pong" effects lead to significant power and area overheads and time to signoff. We propose a novel framework encompassing both global and local clock network optimizations to minimize the sum of skew variations across different PVT corners between all sequentially adjacent sink pairs. The global optimization uses linear programming to guide buffer insertion, buffer removal and routing detours. The local optimization is based on machine learning-based predictors of latency change; these are used for iterative optimization with tree surgery, buffer sizing and buffer displacement operators. Our optimization achieves up to 22% total skew variation reduction across multiple testcases implemented in foundry 28nm technology, as compared to a best-practices CTS solution using a leading commercial tool.

Many areas of science currently use computing resources as a important part of their research, and many research groups adopt cluster architecture to use them efficiently and manage them easily. Therefore, faulttolerance becomes a very important property for the computing resources. However, fault-tolerant systems have not yet been widely adopted because they are either hard to deploy, hard to use, hard to manage, hard to maintain, or hard to justify. This paper proposes a practical fault-tolerant system for eScience infrastructures. Our system uses checkpoint/ restart mechanism for fault-tolerance, and provides a easy mechanism to integrate with Grid services widely used in eScience. Additionally, we run rigorous tests using scientific applications to verify that our system can be used in clusters. We also describe improvements made to our system to solve various problems that arose when deploying it on a cluster. The experimental results show that not only does our system conform to various types of running environment well, but that it can also be practically deployed in clusters.