Many recent studies have shown the ability of large language models (LLMs) to achieve state-of-the-art performance on many NLP tasks, such as question answering, text summarization, coding, and translation. In some cases, the results provided by LLMs are on par with those of human experts. These models' most disruptive innovation is their ability to perform tasks via zero-shot or few-shot prompting. This capability has been successfully exploited to train instructed LLMs, where reinforcement learning with human feedback is used to guide the model to follow the user's requests directly. In this paper, we investigate the ability of instructed LLMs to improve conversational search effectiveness by rewriting user questions in a conversational setting. We study which prompts provide the most informative rewritten utterances that lead to the best retrieval performance. Reproducible experiments are conducted on publicly-available TREC CAST datasets. The results show that rewriting conversational utterances with instructed LLMs achieves significant improvements of up to 25.2% in MRR, 31.7% in Precision@1, 27% in NDCG@3, and 11.5% in Recall@500 over state-of-the-art techniques.

Conversational search has been regarded as the next-generation search paradigm. Constrained by data scarcity, most existing methods distill the well-trained ad-hoc retriever to the conversational retriever. However, these methods, which usually initialize parameters by query reformulation to discover contextualized dependency, have trouble in understanding the dialogue structure information and struggle with contextual semantic vanishing. In this paper, we propose \fullmodel (\model) which is a new post-training paradigm with three self-supervised tasks to efficiently initialize the conversational search model to enhance the dialogue structure and contextual semantic understanding. Furthermore, the \model can be plugged into most of the existing conversational models to boost their performance. To verify the effectiveness of our proposed method, we apply the conversational encoder post-trained by \model on the conversational search task using two benchmark datasets: CAsT-19 and CAsT-20. Extensive experiments that our \model can boost the performance of several existing conversational search methods. Our source code is available at \url{https://github.com/morecry/SSP}.

An AI-based home screening test to detect oral and throat cancers from saliva samples is now available in the United States with the hope of transforming oral and throat cancer detection. Based on a technology approved by the US Food and Drug Administration (FDA) as a "breakthrough device," the saliva test can detect early symptoms of oral and throat cancer with more than 90 percent accuracy. Due to a lack of effective diagnostic tools, these cancers often go undiagnosed until they have reached an advanced stage, resulting in low survival rates. In a previous study, Maria Soledad Sosa from the Icahn School of Medicine at Mount Sinai and Julio A. Aguirre-Ghiso, now at Albert Einstein College of Medicine, discovered that the ability of cancer cells to remain dormant is controlled by a protein called NR2F1. This receptor protein can enter the cell nucleus and turn numerous genes on or off to activate a program that prevents the cancer cells from proliferating.

Top Gun: Maverick has proven to be a massive success for Tom Cruise, Paramount Pictures, and everyone involved. If you've watched the movie by now, you'll probably agree with most of us that it's an excellent follow-up to the original film from 1986. What you might not know is that Val Kilmer's voice in the movie was brought to life with voice AI. When the original Top Gun was released in 1986, Val Kilmer and Tom Cruise's chemistry on-screen as Iceman and Maverick was an instant hit. Revisiting that story without Kilmer's Iceman would have been disappointing for many fans and even for Kilmer himself.

A new diagnostic tool uses artificial intelligence to detect oral and throat cancers from saliva samples with more than 90 per cent accuracy. Estimates suggest there will be 54,000 new cases of oral cancer and 20,640 new cases of oesophageal cancer in the US alone this year. The respective 5-year survival rates for these cancers are 68 and 20.6 per cent, but when detected early, those numbers jump to more than 86 and 47 per cent. The issue is that most oral and throat cancers aren't detected early. Current screening methods rely on visual examinations by a healthcare provider.

A new artificial intelligence program has been developed that can mimic flirty speech patterns, thanks to new'non-word sounds' including sighs and breaths. Sonantic, based in London, England, produces expressive artificial intelligence voices for a range of uses, including Hollywood movies and computer games. The latest development was built with an'unnamed Hollywood client' called'What's Her Secret?', designed to create a flirty female lead character'that has never lived'. They released a video, with the face of an actress but voice of AI, designed to demonstrate it is possible to create'hyper-realistic romantic encounters.' In developing the flirty AI, the team also discovered some secrets that humans can use to sound more romantic and flirty, including slowing down to create suspense, gently smiling when speaking, and keeping a sooth, consistent pace.

Surgery in 2014 forever altered Kilmer's natural voice. The Iceman will not be silenced. Beloved actor Val Kilmer of Top Gun, Tombstone and Willow fame, among many others, lost his voice -- and his career -- to throat cancer after a tracheotomy in 2014. In 2020, Kilmer turned to British AI company Sonantic to create a model of his voice, basically a custom-built audio-only deepfake for the actor's personal use. Sonantic creates voice models primarily for video games using actors who read hours worth of scripts.

A British artificial intelligence (AI) company has recreated Hollywood actor Val Kilmer's voice – with amazingly realistic results. London-based firm Sonantic used the actor's voice recordings from throughout his career, which were fed to their AI to create the lifelike yet artificial mock-up. Film producers could potentially use the tool – described as'Photoshop for voice' – for voiceovers if they have a role in mind that would be suited to Kilmer's tones. Kilmer, whose career has spanned nearly four decades, has starred in blockbusters such as Top Gun, Willow, The Doors, Tombstone and Batman Forever. But after undergoing a tracheotomy in 2014 as part of his treatment for throat cancer, Kilmer's voice is now barely recognisable.

Experts fear the U.S. will see thousands more cancer deaths in the coming years due to delayed screenings, treatments and trials; Dr. Marc Siegel reacts. Throat cancer is a term that can apply to several different types of cancers that occur in different locations in the head and neck. In 2018, more than 30,000 people in the U.S. received a throat cancer diagnosis of some kind, according to MD Anderson Cancer Center. Both laryngeal and hypopharyngeal cancers start in the lower part of the throat. Patients diagnosed with laryngeal cancer mean that the disease was detected in an area affecting the voice box, including the supraglottis, which is located above the vocal cords, the glottis, which contains the vocal cords or the subglottis, which is below the vocal cords, according to the American Cancer Society.

Margaret Thatcher's remarkable success at the ballot box may have been partially due to her distinctive voice, according to a new study. Experts looked at whether voters could be swayed by the way politicians speak. They found that politicians whose voices were hoarse, flat or slow received a better response from the public than those who had a different speech pattern. They believe this is because they are perceived as wiser and more competent than those who have a high-pitched voice. Margaret Thatcher's remarkable success at the ballot box may have been partially due to her distinctive voice, according to a new study.