Recent advances in language and speech modelling have made it possible to build autonomous voice assistants that understand and generate human dialogue in real time. These systems are increasingly being deployed in domains such as customer service and healthcare care, where they can automate repetitive tasks, reduce operational costs, and provide constant support around the clock. In this paper, we present a general methodology for cloning a conversational voice AI agent from a corpus of call recordings. Although the case study described in this paper uses telesales data to illustrate the approach, the underlying process generalizes to any domain where call transcripts are available. Our system listens to customers over the telephone, responds with a synthetic voice, and follows a structured playbook learned from top performing human agents. We describe the domain selection, knowledge extraction, and prompt engineering used to construct the agent, integrating automatic speech recognition, a large language model based dialogue manager, and text to speech synthesis into a streaming inference pipeline. The cloned agent is evaluated against human agents on a rubric of 22 criteria covering introduction, product communication, sales drive, objection handling, and closing. Blind tests show that the AI agent approaches human performance in routine aspects of the call while underperforming in persuasion and objection handling. We analyze these shortcomings and refine the prompt accordingly. The paper concludes with design lessons and avenues for future research, including large scale simulation and automated evaluation.

The last time you called a customer service hotline and it asked you about what issues you are facing and was able to give you more information, did you ever wonder about how all that is working? Well, you don't have nothing to worry about at all as Khalil Faraj & I (Fawaz Siddiqi) are here to tell you about how you can make a Voice Agent with Twilio and Watson Assistant. On the 11th of October, Khalil and I conducted a webinar about how a voice activated chatbot is made and how easy are the steps to make it, we covered various technologies such as Watson Assistant, Watson Speech to Text, Watson Text to Speech, Watson Voice Agent and integrated them with Twilio and vice versa. In addition, we also talked about the pipeline of making a chatbot, on the conversational design as well as the steps involved and what things we should take care of when making a conversational design. The webinar was divided into two parts, the first part was conducted by myself (Fawaz), where I talked about what exactly are chatbots, the types of chatbots and how do they fit in as the last step into our AI cycle, and I would say that this is the final step since this is an external facing tool through which your customers/users can actually interact with the AI based capabilities within your solution and have a human-to-human like interaction (with amazing analytical skills) to get answers to their questions.

Calldesk, the European pioneer in AI-powered voice agents, and Talkdesk, the cloud contact center for innovative enterprises, announced a partnership to accelerate the deployment of conversational AI in contact centers. Via the partnership with Calldesk, Talkdesk customers will now be able to leverage the advantages of conversational AI, by reducing the cost of processing simple requests and providing a better experience to their callers: a personalized response, 24/7, with no hold time, even during call peaks. The Covid-19 crisis has accelerated the transition to cloud contact centers, due to an increase in customer queries as people began working from home. Calldesk's AI-powered voice agents provide an innovative solution to automate repetitive calls in contact centers, in order to manage call spikes, avoid long queue times, and continue to deliver the best customer experience. "We are excited to have Calldesk join the Talkdesk AppConnect partner community. Outstanding AI technology and industry expertise from Calldesk will strengthen and expand the Talkdesk offering," said John Youri, senior vice president, global channels and alliances.

CareCall asks polar questions to monitored subjects, and they need to answer simply'yes' or'no' to the questions. Most of the monitored subjects could easily interact with the voice agent of CareCall. However, since older people tended to respond more freely, it was difficult for the dialog system to classify the utterances of older people. This is a challenging technology issue we need to tackle. Firstly, a voice-based dialog system is required to be able to understand unexpected type of user utterances. Therefore NLU module could be crucial in this voice-based interface.

These days, there's more pressure than ever to deliver secure, seamless, real-time customer service. In fact, 54% of consumers stopped doing business with a company due to bad customer service in 2017, versus 49% in 2016. While 68% of consumers reported increased activity with companies due to good customer service. And these types of customer service experiences are true for every industry, with insurance no exception. It's time that insurance companies understand that they are no longer in control of their brand -- their customers are. And with these customers taking to social media in droves to compare the worst and best experiences that they have had, the need for a seamless user experience designed for resolution is table stakes to win customers and to retain them.

Before my eyes were even open, I spoke to my smart assistant this morning: "Alexa," I asked hopefully, "what time is it?" She kindly replied, "The time is seven twenty-seven a.m." I did not need her to tell me the morning was going to be a struggle. An hour later, dropping the kids off at school, I realized their violins were left in haste by the front door. As I made the U-turn in the school parking lot, I thought to myself, "Inconceivable! I have all this technology surrounding me! How long do I have to wait for this to get easier?"

Inc. said Wednesday its smart speakers will debut in Japan starting next week. Amazon is dominant in the sector overseas, and its entry into the Japan market is expected to further fuel competition. The e-commerce giant said it will offer three Echo speaker models -- Echo, Echo Plus and Echo Dot -- priced at ¥11,980, ¥17,980 and ¥5,980, respectively. The voice-controlled devices are equipped with Alexa, Amazon's AI voice agent. "We are extremely excited to bring Echo and Alexa to Japan," said Tom Taylor, an Amazon senior vice president who overseas Alexa.

Major tech firms have been keen to sell speakers equipped with voice-based artificial intelligence agents recently. The debuts of smart speakers are seen as the prelude to an AI era, ushering in a new technological age in which virtual assistants are expected to become as ubiquitous as the smartphone, allowing people to connect to the internet by voice with greater ease. Whether these speakers will really take off and whether the technology will be popular in Japan remain to be seen. The following are answers to these questions as well as why AI speakers are creating a buzz and what will be the role of Japanese firms in this field. What makes AI speakers special?

Ford cars will soon offer Alexa, but also competitive agents. Amazon's Alexa voice agent has been the biggest surprise hit for the mammoth online retailer since it moved into the cloud storage business with Amazon Web Services. Alexa showed up at CES 2017 in full force. As Larry Dignan notes, the agent picked up friends in high places, including Ford, Whirlpool, Dish Network, Huawei, Hyundai, Mattel, Lenovo, LG, Samsung and ADT. That shouldn't be a surprise to those who noted the rise of Alexa at CES 2016.

Linux-based smart home hubs continue to rule the home automation world, with the latest products integrating voice assistants and AI analytics. Industrial, rather than home, applications will likely dominate the Internet of Things (IoT) market in the years to come. Yet, in the early going, the home automation market has had the greatest visibility. And it hasn't always been pretty. Despite steady growth, retail sales have yet to achieve inflated expectations.