It has been well studied that reliable multicast enables consistency protocols, including Byzantine Fault Tolerant protocols, for distributed systems. However, no transport-layer reliable multicast is used today due to limitations with existing switch fabrics and transport-layer protocols. In this paper, we introduce a layer-4 (L4) transport based on remote direct memory access (RDMA) datagram to achieve reliable multicast over a shared optical medium. By connecting a cluster of networking nodes using a passive optical cross-connect fabric enhanced with wavelength division multiplexing, all messages are broadcast to all nodes. This mechanism enables consistency in a distributed system to be maintained at a low latency cost. By further utilizing RDMA datagram as the L4 protocol, we have achieved a low-enough message loss-ratio (better than one in 68 billion) to make a simple Negative Acknowledge (NACK)-based L4 multicast practical to deploy. To our knowledge, it is the first multicast architecture able to demonstrate such low message loss-ratio. Furthermore, with this reliable multicast transport, end-to-end latencies of eight microseconds or less (< 8us) have been routinely achieved using an enhanced software RDMA implementation on a variety of commodity 10G Ethernet network adapters.

Abstract Automatic speech recognition (ASR) systems often make unrecoverable errors due to subsystem pruning (acoustic, language and pronunciation models); for example, pruning words due to acoustics using short-term context, prior to rescoring with long-term context based on linguistics. In this work, we model ASR as a phrase-based noisy transformation channel and propose an error correction system that can learn from the aggregate errors of all the independent modules constituting the ASR and attempt to invert those. The proposed system can exploit long-term context using a neural network language model and can better choose between existing ASR output possibilities as well as re-introduce previously pruned or unseen (Out-Of-Vocabulary) phrases. It provides corrections under poorly performing ASR conditions without degrading any accurate transcriptions; such corrections are greater on top of out-of-domain and mismatched data ASR. Our system consistently provides improvements over the baseline ASR, even when baseline is further optimized through Recurrent Neural Network (RNN) language model rescoring. This demonstrates that any ASR improvements can be exploited independently and that our proposed system can potentially still provide benefits on highly optimized ASR. Finally, we present an extensive analysis of the type of errors corrected by our system.

This paper describes automatic music transcription with chord estimation for music audio signals. We focus on the fact that concurrent structures of musical notes such as chords form the basis of harmony and are considered for music composition. Since chords and musical notes are deeply linked with each other, we propose joint pitch and chord estimation based on a Bayesian hierarchical model that consists of an acoustic model representing the generative process of a spectrogram and a language model representing the generative process of a piano roll. The acoustic model is formulated as a variant of non-negative matrix factorization that has binary variables indicating a piano roll. The language model is formulated as a hidden Markov model that has chord labels as the latent variables and emits a piano roll. The sequential dependency of a piano roll can be represented in the language model. Both models are integrated through a piano roll in a hierarchical Bayesian manner. All the latent variables and parameters are estimated using Gibbs sampling. The experimental results showed the great potential of the proposed method for unified music transcription and grammar induction.

Orthogonal frequency division multiplex (OFDM) system is a special cognitive radio system that is widely used in military and civilian applications. As a crucial aspect of spectrum monitoring and electronic countermeasures reconnaissance, it is important to identify the OFDM signal. An identification method based on fractal box dimension and pseudo-inverse spectrum (PIS) has been proposed in this paper for the recognition problem of OFDM signal under multipath channel. Firstly, by theoretically analyzing the fractal box dimension of OFDM signal and single carrier (SC) signal, it can be concluded that the fractal box dimension of OFDM signal and SC signal has obvious differences. Thus, the fractal box dimension of the two types of signal is used to discriminate OFDM signal and SC signal. Then, the PIS of an OFDM signal is constructed according to the characteristics of the OFDM signal. Through theoretical analysis and the experimental simulation, it illustrates that the classification feature could be extracted by detecting the periodical peak of the PIS of OFDM signal and used for identifying OFDM signal in the Gaussian noise. Simulation results demonstrate that the proposed algorithm has better performance than the conventional algorithm based on autocorrelation.

Human experts evaluate singing quality based on many perceptual parameters such as intonation, rhythm, and vibrato, with reference to music theory. We proposed previously the Perceptual Evaluation of Singing Quality (PESnQ) framework that incorporated acoustic features related to these perceptual parameters in combination with the cognitive modeling concept of the telecommunication standard Perceptual Evaluation of Speech Quality to evaluate singing quality. In this study, we present further the study of the PESnQ framework to approximate the human judgments. First, we find that a linear combination of the individual perceptual parameter human scores can predict their overall singing quality judgment. This provides us with a human parametric judgment equation. Next, the prediction of the individual perceptual parameter scores from the PESnQ acoustic features show a high correlation with the respective human scores, which means more meaningful feedback to learners. Finally, we compare the performance of early fusion and late fusion of the acoustic features in predicting the overall human scores. We find that the late fusion method is superior to that of the early fusion method. This work underlines the importance of modeling human perception in automatic singing quality assessment.

In this paper, an automatic exposure compensation method is proposed for image enhancement. For the exposure compensation, a novel image segmentation method based on luminance distribution is also proposed. Most single-image-enhancement methods often cause details to be lost in bright areas in images or cannot sufficiently enhance contrasts in dark regions. The image-enhancement method that uses the proposed compensation method enables us to produce high-quality images which well represent both bright and dark areas by fusing pseudo multi-exposure images generated from a single image. Here, pseudo multi-exposure images are automatically generated by the proposed exposure compensation method. To generate effective pseudo multi-exposure images, the proposed segmentation method is utilized for automatic parameter setting in the compensation method. In experiments, image enhancement with the proposed compensation method outperforms state-of-the-art image enhancement methods including Retinex-based methods, in terms of both entropy and statistical naturalness. Moreover, visual comparison results show that the proposed compensation method is effective in producing images that clearly present both bright and dark areas.

Artificial Intelligence (AI) was the inspiration that shaped computing as we know it today. In this article, I explore why and how AI would continue to inspire computing and reinvent it when Moore's Law is running out of steam. At the dawn of computing, Alan Turing proposed that instead of comprising many different specific machines, the computing machinery for AI should be a Universal Digital Computer, modeled after human computers, which carry out calculations with pencil on paper. Based on the belief that a digital computer would be significantly faster, more diligent and patient than a human, he anticipated that AI would be advanced as software. In modern terminology, a universal computer would be designed to understand a language known as an Instruction Set Architecture (ISA), and software would be translated into the ISA. Since then, universal computers have become exponentially faster and more energy efficient through Moore's Law, while software has grown more sophisticated. Even though software has not yet made a machine think, it has been changing how we live fundamentally. The computing revolution started when the software was decoupled from the computing machinery. Since the slowdown of Moore's Law in 2005, the universal computer is no longer improving exponentially in terms of speed and energy efficiency. It has to carry ISA legacy, and cannot be aggressively modified to save energy. Turing's proposition of AI as software is challenged, and the temptation of making many domain-specific AI machines emerges. Thanks to Deep Learning, software can stay decoupled from the computing machinery in the language of linear algebra, which it has in common with supercomputing. A new universal computer for AI understands such language natively to then become a Native Supercomputer. AI has been and will still be the inspiration for computing. The quest to make machines think continues amid the slowdown of Moore's Law. AI might not only maximize the remaining benefits of Moore's Law, but also revive Moore's Law beyond current technology.

The learning tools necessary to prepare the next generation of students must be shaped by the socio-economic needs of the 21st century. The needs of the 21st century – from rebuilding city scale physical infrastructure to personalized healthcare – not only require learning from the wealth of global information available on the Internet, but also the building of a strong grounding in fundamentals. History has shown that the depth in fundamentals has been achieved through conventional books. Indeed, authoritative books in physical fundamentals have been penned in the 19th century and early 20th century. We present a 21st century cyber-physical learning platform that combines the best of physical books with information systems. The systemic instantiation of the platform combines modern optics and computing to view books, scan objects, and enable interactive learning – while simultaneously benefitting from the vast pool of information on the Internet. The hybrid learning platform preserves the best of the past to pave the way for the future. It also enables future research such as meta-data and descriptive tagging of the large number of images available on the web.

This paper proposes a novel model estimation method, which uses nested Gibbs sampling to develop a mixture-of-mixture model to represent the distribution of the model's components with a mixture model. This model is suitable for analyzing multilevel data comprising frame-wise observations, such as videos and acoustic signals, which are composed of frame-wise observations. Deterministic procedures, such as the expectation–maximization algorithm have been employed to estimate these kinds of models, but this approach often suffers from a large bias when the amount of data is limited. To avoid this problem, we introduce a Markov chain Monte Carlo-based model estimation method. In particular, we aim to identify a suitable sampling method for the mixture-of-mixture models. Gibbs sampling is a possible approach, but this can easily lead to the local optimum problem when each component is represented by a multi-modal distribution. Thus, we propose a novel Gibbs sampling method, called “nested Gibbs sampling,” which represents the lower-level (fine) data structure based on elemental mixture distributions and the higher-level (coarse) data structure based on mixture-of-mixture distributions. We applied this method to a speaker clustering problem and conducted experiments under various conditions. The results demonstrated that the proposed method outperformed conventional sampling-based, variational Bayesian, and hierarchical agglomerative methods.

This paper describes the progress in frequency-domain linear prediction coding (LPC)-based audio coding schemes. Although LPC was originally used only for time-domain speech coders, it has been applied to frequency-domain coders since the late 1980s. With the progress in associated technologies, the frequency-domain LPC-based audio coding scheme has become more promising, and it has been used in speech/audio coding standards, such as MPEG-D unified speech and audio coding and 3GPP enhanced voice services since 2010. Three of the latest investigations on the representations of LPC envelopes in frequency-domain coders are shown. These are the harmonic model, frequency-resolution warping and the Powered All-Pole Spectral Envelope, all of which are aiming at further enhancement of the coding efficiency.