In this interview, News-Medical speaks to Zoë Thomson, Co-founder and Chief Innovation Officer of LUCID, about how music and machine learning are changing how we approach mental and neuropsychiatric health. I was motivated to begin this work because, through my background as a biomedical engineer and researcher, I observed an abundance of technical capabilities in this current age around biosignals and artificial intelligence (AI). I was interested in how these tools could be leveraged to deliver more personalized and effective care. I didn't see these capabilities fully instantiated within the mental health care paradigm, which is relatively "one-size-fits-all," while the stigma around traditional interventions like medication and therapy continues to limit access to care. As a result, I saw a real need for novel approaches to mental health interventions.

Speaker adaptation is important to build robust automatic speech recognition (ASR) systems. In this work, we investigate various methods for speaker adaptive training (SAT) based on feature-space approaches for a conformer-based acoustic model (AM) on the Switchboard 300h dataset. We propose a method, called Weighted-Simple-Add, which adds weighted speaker information vectors to the input of the multi-head self-attention module of the conformer AM. Using this method for SAT, we achieve 3.5% and 4.5% relative improvement in terms of WER on the CallHome part of Hub5'00 and Hub5'01 respectively. Moreover, we build on top of our previous work where we proposed a novel and competitive training recipe for a conformer-based hybrid AM. We extend and improve this recipe where we achieve 11% relative improvement in terms of word-error-rate (WER) on Switchboard 300h Hub5'00 dataset. We also make this recipe efficient by reducing the total number of parameters by 34% relative.

Despite analyst predictions that the Artificial Intelligence (AI) industry will be worth £49 billion globally in 2022, a new in-depth study by BT has uncovered a lack of awareness amongst UK students about the opportunity to pursue qualifications in AI related courses. Where almost three in five (59%) higher education students said they were unaware of AI courses at the time of choosing their course, over half (51%) revealed that they would consider studies centred around AI in the future, once they had understood and received more information about what the courses entail. The findings are revealed in BT's report, AI skills: Motivation & AI careers myths debunked, which was commissioned in partnership with Yonder Consultancy, to understand how to grow and retain AI talent in the UK. Identifying additional challenges connected to the attraction of talent to the UK AI industry, the study found that 38% of higher education students perceive a career in AI to be dull while 42% believe that AI qualifications wouldn't give them the career they are looking for. Despite these perception issues, 66% of higher education students believe the AI industry to be full of ambitious people, and almost three quarters (73%) believe it to be a career that would allow them to solve problems.

Mphasis accelerates the world-leading Quantum Computing Ecosystem in partnership with the University of Calgary and the Government of Alberta. The Quantum Lab is set to accelerate the development of quantum skills in the city to enable job creation. CALGARY, AB, June 9, 2022 – Mphasis, (BSE: 526299; NSE: MPHASIS), an Information Technology (IT) solutions provider specializing in cloud and cognitive services, today joined the Government of Alberta and the University of Calgary to announce the launch of the world-leading Quantum City – Canada. Quantum city will further establish Alberta as a leading technology hub and will accelerate the development of the quantum ecosystem in Calgary. The partnership aims to utilize the synergy between academia, industry, and government to put the process of ideation to market at the forefront.

Finest security and threat administration practices can mitigate legal responsibility publicity. Because the trade matures, and operations turn into extra advanced, now greater than ever, drone insurance coverage ought to issue closely in enterprise choices. On this article, Elad Shalev, Advertising and marketing Supervisor at SkyWatch.AI, drone trade insurance coverage leaders, offers insights into the highest three trade and accident developments, in addition to ideas to assist drone companies soar. Based in 2018, SkyWatch.AI was one of many first corporations to make use of expertise, analytics and telematics to higher assess the dangers of drone operations. That knowledge in the end knowledgeable a variety of plans to scale back threat for drone operators globally.

A former Marine from Orange County has been arrested and faces federal charges for allegedly creating hundreds of Twitter accounts used to stalk a professional video game player who lives in Calgary, Canada, authorities said. Evan Baltierra, 29, was arrested Monday by FBI agents at his home in Trabuco Canyon on suspicion of stalking, according to federal prosecutors. He admitted to investigators he harassed the woman who made her living as a professional online gamer on the popular "War of Warcraft," authorities said. The suspect "orchestrated a campaign of harassment targeting the victim, her boyfriend, her friends and her boyfriend's family," according to court records. Baltierra and his attorney could not be reached for comment.

Contextual knowledge is essential for reducing speech recognition errors on high-valued long-tail words. This paper proposes a novel tree-constrained pointer generator (TCPGen) component that enables end-to-end ASR models to bias towards a list of long-tail words obtained using external contextual information. With only a small overhead in memory use and computation cost, TCPGen can structure thousands of biasing words efficiently into a symbolic prefix-tree and creates a neural shortcut between the tree and the final ASR output to facilitate the recognition of the biasing words. To enhance TCPGen, we further propose a novel minimum biasing word error (MBWE) loss that directly optimises biasing word errors during training, along with a biasing-word-driven language model discounting (BLMD) method during the test. All contextual ASR systems were evaluated on the public Librispeech audiobook corpus and the data from the dialogue state tracking challenges (DSTC) with the biasing lists extracted from the dialogue-system ontology. Consistent word error rate (WER) reductions were achieved with TCPGen, which were particularly significant on the biasing words with around 40\% relative reductions in the recognition error rates. MBWE and BLMD further improved the effectiveness of TCPGen and achieved more significant WER reductions on the biasing words. TCPGen also achieved zero-shot learning of words not in the audio training set with large WER reductions on the out-of-vocabulary words in the biasing list.

Across midwestern farms, if Girish Chowdhary has his way, farmers will someday release beagle-sized robots into their fields like a pack of hounds flushing pheasant. The robots, he says, will scurry in the cool shade beneath a wide diversity of plants, pulling weeds, planting cover crops, diagnosing plant infections, and gathering data to help farmers optimize their farms. Chowdhary, a researcher at the University of Illinois, works surrounded by corn, one of the most productive monocultures in the world. In the United States, the corn industry was valued at $82.6 billion in 2021, but it -- like almost every other segment of the agricultural economy -- faces daunting problems, including changing weather patterns, environmental degradation, severe labor shortages, and the rising cost of key supplies, or inputs: herbicides, pesticides, and seed. Agribusiness as a whole is betting that the world has reached the tipping point where desperate need caused by a growing population, the economic realities of conventional farming, and advancing technology converge to require something called precision agriculture, which aims to minimize inputs and the costs and environmental problems that go with them. No segment of agriculture is without its passionate advocates of robotics and artificial intelligence as solutions to, basically, all the problems facing farmers today.

Thirteen university students from across Canada are in Ottawa to put their artificial intelligence skills to the test. It's called the Amazon Web Services DeepRacer League, where small 1/18th scale cars are being trained to complete a racetrack as fast as possible, by themselves. "It has major components in order to do the autonomous driving," says Amanda Foo, DeepRacer Senior Technical Program Manager. They are driven by what is called reinforcement learning. "It's just like training a dog," Carleton University mechanical engineering student Masoud Karimi says.

Objective: Epileptic seizures are relatively common in critically-ill children admitted to the pediatric intensive care unit (PICU) and thus serve as an important target for identification and treatment. Most of these seizures have no discernible clinical manifestation but still have a significant impact on morbidity and mortality. Children that are deemed at risk for seizures within the PICU are monitored using continuous-electroencephalogram (cEEG). cEEG monitoring cost is considerable and as the number of available machines is always limited, clinicians need to resort to triaging patients according to perceived risk in order to allocate resources. This research aims to develop a computer aided tool to improve seizures risk assessment in critically-ill children, using an ubiquitously recorded signal in the PICU, namely the electrocardiogram (ECG). Approach: A novel data-driven model was developed at a patient-level approach, based on features extracted from the first hour of ECG recording and the clinical data of the patient. Main results: The most predictive features were the age of the patient, the brain injury as coma etiology and the QRS area. For patients without any prior clinical data, using one hour of ECG recording, the classification performance of the random forest classifier reached an area under the receiver operating characteristic curve (AUROC) score of 0.84. When combining ECG features with the patients clinical history, the AUROC reached 0.87. Significance: Taking a real clinical scenario, we estimated that our clinical decision support triage tool can improve the positive predictive value by more than 59% over the clinical standard.