Summary Solutions to many of the world's problems depend upon materials research and development. However, advanced materials can take decades to discover and decades more to fully deploy. Humans and robots have begun to partner to advance science and technology orders of magnitude faster than humans do today through the development and exploitation of closed-loop, autonomous experimentation systems. This review discusses the specific challenges and opportunities related to materials discovery and development that will emerge from this new paradigm. Our perspective incorporates input from stakeholders in academia, industry, government laboratories, and funding agencies. We outline the current status, barriers, and needed investments, culminating with a vision for the path forward. We intend the article to spark interest in this emerging research area and to motivate potential practitioners by illustrating early successes. We also aspire to encourage a creative reimagining of the next generation of materials science infrastructure. To this end, we frame future investments in materials science and technology, hardware and software infrastructure, artificial intelligence and autonomy methods, and critical workforce development for autonomous research.

Autonomous experimentation systems for materials development: A community perspective

Speaker recognition is a task of identifying persons from their voices. Recently, deep learning has dramatically revolutionized speaker recognition. However, there is lack of comprehensive reviews on the exciting progress. 
In this paper, we review several major subtasks of speaker recognition, including speaker verification, identification, diarization, and robust speaker recognition, with a focus on deep-learning-based methods. Because the major advantage of deep learning over conventional methods is its representation ability, which is able to produce highly abstract embedding features from utterances, we first pay close attention to deep-learning-based speaker feature extraction, including the inputs, network structures, temporal pooling strategies, and objective functions respectively, which are the fundamental components of many speaker recognition subtasks. Then, we make an overview of speaker diarization, with an emphasis of recent supervised, end-to-end, and online diarization. Finally, we survey robust speaker recognition from the perspectives of domain adaptation and speech enhancement, which are two major approaches of dealing with domain mismatch and noise problems. Popular and recently released corpora are listed at the end of the paper.

Speaker Recognition Based on Deep Learning: An Overview

Speaker recognition based on deep learning: An overview

A study of 1304 data points collated over 266 papers statistically evaluates the relationships between carbon nanotube (CNT) material characteristics, including: electrical, mechanical, and thermal properties; ampacity; density; purity; microstructure alignment; molecular dimensions and graphitic perfection; and doping. Compared to conductive polymers and graphitic intercalation compounds, which have exceeded the electrical conductivity of copper, CNT materials are currently one-sixth of copper's conductivity, mechanically on-par with synthetic or carbon fibers, and exceed all the other materials in terms of a multifunctional metric. Doped, aligned few-wall CNTs (FWCNTs) are the most superior CNT category; from this, the acid-spun fiber subset are the most conductive, and the subset of fibers directly spun from floating catalyst chemical vapor deposition are strongest on a weight basis. The thermal conductivity of multiwall CNT material rivals that of FWCNT materials. Ampacity follows a diameter-dependent power-law from nanometer to millimeter scales. Undoped, aligned FWCNT material reaches the intrinsic conductivity of CNT bundles and single-crystal graphite, illustrating an intrinsic limit requiring doping for copper-level conductivities. Comparing an assembly of CNTs (forming mesoscopic bundles, then macroscopic material) to an assembly of graphene (forming single-crystal graphite crystallites, then carbon fiber), the ≈1 µm room-temperature, phonon-limited mean-free-path shared between graphene, metallic CNTs, and activated semiconducting CNTs is highlighted, deemphasizing all metallic helicities for CNT power transmission applications.

https://onlinelibrary.wiley.com/doi/pdf/10.1002/adma.202008432

A Meta-Analysis of Conductive and Strong Carbon Nanotube Materials.

Autonomous experimentation driven by artificial intelligence (AI) provides an exciting opportunity to revolutionize inorganic materials discovery and development. Herein, we review recent progress in the design of self-driving laboratories, including robotics to automate materials synthesis and characterization, in conjunction with AI to interpret experimental outcomes and propose new experimental procedures. We focus on efforts to automate inorganic synthesis through solution-based routes, solid-state reactions, and thin film deposition. In each case, connections are made to relevant work in organic chemistry, where automation is more common. Characterization techniques are primarily discussed in the context of phase identification, as this task is critical to understand what products have formed during synthesis. The application of deep learning to analyze multivariate characterization data and perform phase identification is examined. To achieve “closed-loop” materials synthesis and design, we further provide a detailed overview of optimization algorithms that use active learning to rationally guide experimental iterations. Finally, we highlight several key opportunities and challenges for the future development of self-driving inorganic materials synthesis platforms.

/pdf/toward-autonomous-design-and-synthesis-of-novel-inorganic-172g5itji4.pdf

Toward autonomous design and synthesis of novel inorganic materials

Deep neural network (DNN) embeddings for speaker recognition have recently attracted much attention. Compared to i-vectors, they are more robust to noise and room reverberation as DNNs leverage large-scale training. This article addresses the question of whether speech enhancement approaches are still useful when DNN embeddings are used for speaker recognition. We investigate single- and multi-channel speech enhancement for text-independent speaker verification based on x-vectors in conditions where strong diffuse noise and reverberation are both present. Single-channel (monaural) speech enhancement is based on complex spectral mapping and is applied to individual microphones. We use masking-based minimum variance distortion-less response (MVDR) beamformer and its rank-1 approximation for multi-channel speech enhancement. We propose a novel method of deriving time-frequency masks from the estimated complex spectrogram. In addition, we investigate gammatone frequency cepstral coefficients (GFCCs) as robust speaker features. Systematic evaluations and comparisons on the NIST SRE 2010 retransmitted corpus show that both monaural and multi-channel speech enhancement significantly outperform x-vector's performance, and our covariance matrix estimate is effective for the MVDR beamformer.

Robust Speaker Recognition Based on Single-Channel and Multi-Channel Speech Enhancement

Materials exploration and development for three-dimensional (3D) printing technologies is slow and labor-intensive. Each 3D printing material developed requires unique print parameters be learned for successful part fabrication, and sub-optimal settings often result in defects or fabrication failure. To address this, we developed the Additive Manufacturing Autonomous Research System (AM ARES). As a preliminary test, we tasked AM ARES with autonomously modulating four print parameters to direct-write single-layer print features that matched target specifications. AM ARES employed automated image analysis as closed-loop feedback to an online Bayesian optimizer and learned to print target features in fewer than 100 experiments. In due course, this first-of-its-kind research robot will be tasked with autonomous multi-dimensional optimization of print parameters to accelerate materials discovery and development in the field of AM. The combining of open-source ARES OS software with low-cost hardware makes autonomous AM highly accessible, promoting mainstream adoption and rapid technological advancement. The discovery and development of new materials and processes for three-dimensional (3D) printing is hindered by slow and labor-intensive trial-and-error optimization processes. Coupled with a pervasive lack of feedback mechanisms in 3D printers, this has inhibited the advancement and adoption of additive manufacturing (AM) technologies as a mainstream manufacturing approach. To accelerate new materials development and streamline the print optimization process for AM, we have developed a low-cost and accessible research robot that employs online machine learning planners, together with our ARES OS software, which we will release to the community as open-source, to rapidly and effectively optimize the complex, high-dimensional parameter sets associated with 3D printing. In preliminary trials, the first-of-its-kind research robot, the Additive Manufacturing Autonomous Research System (AM ARES), learned to print single-layer material extrusion specimens that closely matched targeted feature specifications in under 100 iterations. Delegating repetitive and high-dimensional cognitive labor to research robots such as AM ARES frees researchers to focus on more creative, insightful, and fundamental scientific work and reduces the cost and time required to develop new AM materials and processes. The teaming of human and robot researchers begets a synergy that will exponentially propel technological progress in AM.

/pdf/toward-autonomous-additive-manufacturing-bayesian-328uokzfoo.pdf

Toward autonomous additive manufacturing: Bayesian optimization on a 3D printer

A major technological challenge in materials research is the large and complex parameter space, which hinders experimental throughput and ultimately slows down development and implementation. In single-walled carbon nanotube (CNT) synthesis, for instance, the poor yield obtained from conventional catalysts is a result of limited understanding of input-to-output correlations. Autonomous closed-loop experimentation combined with advances in machine learning (ML) is uniquely suited for high-throughput research. Among the ML algorithms available, Bayesian optimization (BO) is especially apt for exploration and optimization within such high-dimensional and complex parameter space. BO is an adaptive sequential design algorithm for finding the global optimum of a black-box objective function with the fewest possible measurements. Here, we demonstrate a promising application of BO in CNT synthesis as an efficient and robust algorithm which can (1) improve the growth rate of CNT in the BO-planner experiments over the seed experiments up to a factor 8; (2) rapidly improve its predictive power (or learning); (3) Consistently achieve good performance regardless of the number or origin of seed experiments; (4) exploit a high-dimensional, complex parameter space, and (5) achieve the former 4 tasks in just over 100 hundred experiments (~8 experimental hours) - a factor of 5× faster than our previously reported results.

/pdf/efficient-closed-loop-maximization-of-carbon-nanotube-growth-29qo0ufrs8.pdf

Efficient Closed-loop Maximization of Carbon Nanotube Growth Rate using Bayesian Optimization.

Recent research shows that the i-vector framework for speaker recognition can significantly benefit from phonetic information. A common approach is to use a deep neural network (DNN) trained for automatic speech recognition to generate a universal background model (UBM). Studies in this area have been done in relatively clean conditions. However, strong background noise is known to severely reduce speaker recognition performance. This study investigates a phonetically-aware i-vector system in noisy conditions. We propose a front-end to tackle the noise problem by performing speech separation and examine its performance for both verification and identification tasks. The proposed separation system trains a DNN to estimate the ideal ratio mask of the noisy speech. The separated speech is then used to extract enhanced features for the i-vector framework. We compare the proposed system against a multi-condition trained baseline and a traditional GMM-UBM i-vector system. Our proposed system provides an absolute average improvement of 8% in identification accuracy and 1.2% in equal error rate.

Jorge Chang

Papers

Robust Speaker Recognition Based on Single-Channel and Multi-Channel Speech Enhancement

Toward autonomous additive manufacturing: Bayesian optimization on a 3D printer

Efficient Closed-loop Maximization of Carbon Nanotube Growth Rate using Bayesian Optimization.

Robust speaker recognition based on DNN/i-vectors and speech separation

Data-driven experimental design and model development using Gaussian process with active learning.