SEARCH

95 results found

Blog Posts (45)

  • Audio data with deep learning - the next frontier

    Introduction Artificial intelligence (AI) has become an inherent part of our lives and machine learning is driving to solve new problems every day. With the recent advancements in deep learning, most AI practitioners agree that AI's impact is exponentially expanding year after year. This, of course, has been with the help of big data and unstructured data. These two types of data are not synonymous. Big data can be structured or unstructured and has three characteristics - volume, velocity (speed with which it arrives) and variety (different types like pictures, videos etc.) in data. Unstructured data, on the other hand, refers to data that is not organized or repetitive and is oftentimes large in volume and velocity and thus can be synonymously referred to as big data. Two well-known examples of unstructured data are images and text. Image data is used to solve complex computer vision problems such as facial recognition and autonomous cars. Text data, on the other hand, is used to solve Natural Language Processing (NLP) problems such as understanding spoken language or translating from one language to another (refer to our NLP blog here). Because of its applications, image and text data have received a lot of attention. Along with images and text, there's a third type of unstructured data - audio data. Audio data is less well known, and we'll be diving into it in this writing. This type of data comes in the form of audio files (.wav, .mp3 etc.) or streaming audio. Most applications of audio data are in the music domain in the form of music cataloging or lyric generation. Complexity of audio data has limited it from finding mainstream applications. This has changed with the rapid development in the field of deep learning. Audio data applications Audio data is used to build AI models that perform automatic speech recognition (ASR). ASR solves problems such as understanding what is said to a voice assistant such as Alexa or Siri or converting speech to text for applications such as voice bots and automatic medical transcription. In addition to ASR, audio data is also used to solve problems such as speaker detection, speaker verification and speaker diarization. Applications of speaker detection include Alexa’s ability to change responses based on who is speaking or identifying speakers in a live-streaming audio or video. An application of speaker verification is biometric security. Speaker diarization refers to separating audio to identify who is speaking “what” and “when”. A common application of speaker diarization is transcribing meeting recordings or phone conversations by speaker. As this technology ripens, many more applications are possible that would be based on conversations between people e.g., automatic test result generation for school verbal tests, mental health diagnosis based on conversations. Features of audio data Unlike text and image data, audio data has hidden characteristics in its signal which tend to be more difficult to mine. Most audio data available today is digitized. The digitization process stores audio signals by sampling them. The sampling rate varies by the type of media. For example, CD quality audio uses a sampling rate of 44,100. This means that audio data is sampled 44,100 times in a second and stored in a digital format. Each sample value represents the intensity or amplitude of the sound signal. This sampled data can be processed further to extract features depending on what kind of analysis is required. Spectral features that are based on the frequency domain are probably the most useful. Examples of such features and their applications are as follows (there are many more): 1. Mel Frequency Cepstral Coefficients (MFCC) - represents the envelope of time power spectrum which represent sounds made by a human vocal tract 2. Zero crossing rate – used to detect percussive sounds and a good feature for classifying musical genres 3. Average Energy – can represent formants which uniquely identify a human voice 4. Spectral entropy – used to detect silence A speech model will extract the above features depending on the application and use them in a supervised or unsupervised machine learning model or in a deep learning model. Models for speaker detection, verification and speaker diarization Models for speaker detection and speaker verification are classification problems. For speaker detection, audio features must be extracted for each speaker. The audio feature data can be fed to a neural network which can then be trained. Models for speaker diarization have historically been unsupervised clustering problems but newer models are based on neural networks. Speech model performance Performance of speech models have yet to overcome the following challenges: (1) poor accuracy in recordings of people of the same gender or of people with different accents (2) poor accuracy of speech to text due to language complexities and (3) inability to deal with background noises. The first challenge can be overcome with more training data. New methodologies in bringing together acoustic data and text data is addressing the second challenge. Speech denoising (removal of background noise) is another area that requires a lot of noise and quiet speech samples. Overall, one can expect that speech models will perform better with more varied data. This is the case for deep learning models in other areas as well. As building complex deep learning models becomes easier with various frameworks, a majority of the work is in understanding and preparing the data. Conclusion Audio data is coming into prime time along with its cousins – image and text data. The main driver for it has been deep learning. Applications such as voice assistants and voice bots have entered the mainstream due to this technology development. With a broad spectrum of models in the area of ASR, speaker detection, speaker verification and speaker diarization, we can expect a larger array of conversation-based applications. Crossing this frontier will require integrating multiple types of data and preparing them well so that they are ingested by advanced models to produce good predictions. About Cedrus: Cedrus Digital is involved in studying audio and conversation data and provides strategies on how information can be harvested from them. Cedrus Digital provides analytics and data science services to gain visibility into high volume call center inquiries – creating opportunities for process efficiencies and high value Conversational AI call center solutions and supplementation. Chitra Sharathchandra is a Data Scientist who enjoys working on implementable AI solutions related to multiple types of data

  • NLP Introduction - How AI Understands Our Communication Patterns

    Introduction I know like me, as a child, you probably daydreamed about how amazing life would be like to have a walking and talking robot. I used to imagine ordering my robot to make my bed, clean up my room and most definitely do all of my homework! I would have time to spend on the real things that were of much greater importance. Little did I know back then that it is a complicated task to communicate with a machine. Communication is often a two-way process. It is necessary to not only express our thoughts impeccably but to comprehend others’ words without our biases. It is a bonus if we can predict others’ words! It is clear that communication is critical, and to communicate well is a very desirable skill. According to a popular Holmes Report on “The Cost of Poor Communications”, the cost of inadequate communication is staggering for businesses. It is evident that companies that have leaders who are highly effective communicators have relevant business models, higher profits and at least 50% higher returns to shareholders. They constantly seek to learn how they can serve their customers and in turn grow their profits. Diving into The Complexity of Language So, what makes understanding human language so difficult to understand? It is something to ponder over - we humans are certainly not experts at communicating with each other. How can we communicate with a machine? The challenge is attributed to the dynamism of human language. For example, understanding the query intent is a complex process. If we remove all contextual information, then only the key words remain. This can be quite confusing! How would my robot comprehend my direction “Make my bed!”? Does this mean actually hammering wooden boards to construct a bed structure or does it mean to neatly arrange the bedsheets? This illustrates syntactical complexity in human language. We must keep in mind that all human languages have evolved over thousands of years of speech patterns. Language is essentially a fluid, living entity that develops with the needs and situations of communities. If we think about Shakespearean English and the English we speak today, we can easily notice the drastic contrast. According to Grammarly, in Shakespearean times (late 1500s – early 1600), the words bandit, lonely, critic, dauntless, dwindle, elbow, green-eyed (to describe jealousy) and lackluster were created. It is interesting to observe the turbulence during that time – resulting in the creation of new vocabulary. Additionally, the tone, sentiment and mentality of society was very different – all providing a distinctive filter on communication. The Challenge of Human-Machine Understanding As humans we can use our intuitions and communication experiences to understand even if it something not explicitly stated. In contrast, a machine lacks intuition. However, intuition can be developed with the “experience” of a larger corpus. For example, we have sufficient life experiences to understand what a lion is. A computer cannot comprehend what a lion is as an entity or define its attributes. A computer is exceptional at computing the probability of a lion moving as higher than the probability of a piano moving. Regardless of how many layers of natural language methodologies we implement and the quantity of text, it is impossible to recreate human intuition and experience in a machine. Our best approach in converging on the communication gap between human and machine is to represent words relative to other words within a corpus. Natural language processing (NLP) is an umbrella technology encompassing everything from text parsing to complex statistical methods used in deep learning. The aim is to enable communication between a machine and humans. NLP methodologies process human language. NLP allows computers to communicate and comprehend by reading, editing, summarizing text and even generating text. NLP’s Impact on Machine Learning There are many open-source techniques to aid a machine to understand text. Text embedding techniques, such as Word2vec (from Google) and GloVe (from Stanford), provide a general natural language methodology to cultivate an understanding of words, context, sentiment and intent. Words are represented as a dense vector in a highly dimensional sparse matrix. We build a dense vector so that it is similar to vectors of words that appear in similar contexts. Using these vector representations, it is possible to find how different words in a sentence relate to each other and how they relate collectively. The algorithm goes through each position of a word in the text. The word vectors are iteratively adjusted until this probability is maximized. If a word in a sentence is replaced with a word with a comparable vector representation, we can obtain a similar meaning for the sentence. Word2vec performs wonderfully when we have a large corpus. Word2vec training can be improved by eliminating stopwords from the dataset. Stopwords are high frequency words that add little value to language understanding, and their removal aids in improving model accuracy and training time. About Cedrus: If you’d like a guided approach for implementing NLP on your road towards Enterprise-AI, Cedrus Digital specializes in the AI transformation journey for companies of all sizes. Come work with our experts to set you on your path in not only NLP, but Conversational AI, Vision, Predictive Analytics, and Knowledge Graphs as well. We can help you brainstorm& prioritize use cases, as well as help with planning, management, and delivery of AI projects. Let’s partner together. In future blogposts I will dive deeper into the intricacies of text embedding and explore, with some technical rigor, other aspects of NLP required for successful implementation. Businesses have realized that unstructured and semi-structured data need to be mined using NLP rather than rely on outdated manual or template-based techniques. Natural Language Processing is powerful tool that has an immense impact on the business model and serving the customer. Stay tuned! Swati Sharma, Ph.D. is a Senior AI Solutions Engineer at Cedrus Digital. She teaches and mentors future data scientists and works with clients to create solutions for complex business problems.

  • Steps for a successful migration to Red Hat OpenShift Service on AWS (ROSA)

    Enterprises have an abundance of options when considering their long-term modernization and container strategies. With constant innovation and associated change in this maturing space, it is important to choose a path wisely and to strive for consistency and predictability to maximize what really matters most at the end of the day, business value. As enterprises look to optimize their Kubernetes strategies, Red Hat OpenShift quickly emerges as a leading platform to build upon for a variety of reasons. Aligning containerization benefits with enterprise cloud strategies brings forth another no-brainer in leveraging the market leader, Amazon Web Services (AWS), to drive the ultimate combination of flexibility, scalability, and simplicity, which are historically uncommon attributes when referencing enterprise platform architecture. AWS and Red Hat have been collaborating for years to drive innovative solutions in the rapidly evolving space of enterprise technology. The latest release of Red Hat OpenShift Service on AWS (ROSA) combines the best of both worlds to accelerate application modernization with native streamlined efficiencies that enterprises are seeking in today’s increasingly complex enterprise architecture space. For customers looking to embrace the business benefits that ROSA introduces, it is important to map out a winning strategy to ensure a successful migration. Here are 5 key considerations to consider when planning your ROSA migration. 1) Infrastructure and Platform Analysis · Ensure you have complete visibility of your legacy platform for all applications. Leave no stone unturned. · Identify and plan for all platform gaps and application dependencies. · Map functionalities to OpenShift early in the process. 2) Application Analysis · Catalog all critical applications with key attributes such as internal and external dependencies, underlying language, and framework (with versions). 3) CI/CD Analysis · Validate the accuracy of your current pipeline process from a build, dev, release, prod, and validation perspective. · Adapt pipeline stages to leverage OpenShift standards like Helm and OpenShift Operators. · Plan for future native pipelines including Tekton. 4) Code Automation Analysis · Analyze code for trends to remove and replace or update code as needed. · Consistently feed your tooling to drive measurable improvement with each application. · Slow down to speed up, embrace automation at every possible step. 5) Plan for optimization · Embrace OpenShift’s simplified options for automation and governance as code. · ROSA allows for management though the familiar OpenShift interfaces, with simple integration to a growing list of cutting-edge AWS services. · Identify and plan for the art of the possible once you have reached your destination. Focus on accelerating simple use cases as a first step. Lean on the experts from AWS, Red Hat and their partner ecosystems to help ensure your migration is a success that clearly articulates the associated business value. It is important to include assumed benefits that ROSA also represents with greater ability to focus on innovation and business value by leaving the management and support burden up to the experts at Red Hat and AWS. ROSA introduces a low friction, streamlined platform that will uncover areas of efficiency that are unique to each customer and opens endless possibilities for ongoing focus on modernization and innovation. About Cedrus - Cedrus designs, develops, and implements modern cloud applications that drive digital transformation at global brands. We are a trusted advisor for design thinking, innovation and modernization founded on expertise in cloud security, cloud native application development, cognitive business automation and systems integration. www.cedrus.digital

View All

Pages (50)

  • AWS Kafka MSK | Cedrus Digital

    Amazon MSK to accelerate modernization with Apache Kafka With modernization needs on the rise with highly complex enterprise production workloads, the list of business value use cases for Apache Kafka continues to grow. ​ As cloud native modernization efforts transform the legacy application landscape, alignment with business objectives and overarching SRE objectives is paramount. Amazon MSK provides the building blocks to build business use cases with enterprise scale and security at light speed. Why adopt Event Driven Architecture? Business Intelligence Real Time Data New Data Insights Extreme Agility Independent Microservices Change Anytime Zero Risk Application Extension Unlimited Scalability Distributed Design is Built for Unlimited Linear Scale Increased Uptime Replication is Inherent Failover is Automatic Cost Reduction Mainframe Extension without Loss of Performance TCO Reduction Flexible Cloud Consumption Models Why Amazon MSK? AWS Scale and Security Immediate availability with elastic cluster sizing as needed Highly Available Kafka clusters Business Agility ​​ Drive use cases and POV's quickly and integrate with existing Kafka Fully Managed ​ Focus on Events and modernization, not clusters​ ​ Data Driven ​ Real time data ​consumption supports machine learning and automation needs Digital Transformation ​ Existing systems can; extend value, modernize, scale and enable disruptive user experience​ Why Cedrus? Over 20 years of experience in managing, architecting, and implementing successful enterprise modernization strategies Dedicated Integration, Cloud, and Security practices Solution experts with knowledge of different technology solutions (MQ, Apache Kafka, Serverless, Streaming, and more) Early adopters work hand-in-hand with the Apache Kafka and Amazon MSK team Amazon MSK Methodology Discovery Understand the business impact for EDA Analysis of existing legacy systems Align EDA with a business problem or corporate objective Plan Leverage Domain Driven design to classify applications Cross validation and correlation stakeholder sessions Determine the MVP and promote Pilot MVP / POV Establish the MSK environment Identify producers and consumers Create an event schema / serialization strategy Configure network for access to MSK for applications Migrate one or two low impact, medium complexity applications Migration / Go Live Decompose business flows to identify the microservices and events Evolve to an event-first approach Operationalize and promote to additional application use cases Cedrus Amazon MSK Analysis Experience how Cedrus has helped some of the largest companies in the world transform with Event driven Architecture. Cedrus will help uncover the benefits of Kafka and Amazon MSK with a complimentary EDA workshop. Contact Us AWS Marketplace WANT TO LEARN MORE ? Get in touch with us! We're thrilled to answer your questions and help you define a vision. Contact Us

  • Cedrus Digital | Customized Digital Transformation

    Line separator DIGITAL TRANSFORMATION SOLUTIONS DONE RIGHT Your company is unique; your technology solutions should be too. Our expert consultants advise and aim to tailor our solutions to your specific business needs with unprecedented speed and agility. Why trust your innovation to anyone else? WHAT WE DO FEATURED PARTNERSHIPS OUR VISION To deliver our customers innovative solutions with unparalleled levels of functionality and sophistication, bridging the present into the future, while bringing unprecedented operational efficiencies into their business. WHO WE ARE 82 % Repeat Customers 164 % Customer base growth over the last 4 years 44 % CAGR for the past 3 years About Cedrus We are a young, imaginative, diverse company, deeply rooted in successfully solving large business problems for the past 25 years. Our employees, partners, and customers share our zeal for excellence. Learn more about what makes us special. MEET CEDRUS Our Expertise We tame cutting-edge technologies to fit your business. Our extensive certifications, internal investments in assets and IP, and our experience from hundreds of transformational projects inform our wisdom as we take on new challenges. OUR EXPERTISE HOW WE'RE DIFFERENT We expertly guide you through discovery and design, architecture and development, and production and support, with an approach perfectly tailored to your unique business needs. Realizing your business' potential has never been easier! Learn about our offerings at no commitment, risk, or cost. WHAT WE DO See us in action! Get to know our work through some real-life examples. Take a look at some use cases, demos, and solutions that others are already implementing . USE CASES Grow with us! WE ARE HIRING! Want to be part of a dynamic, creative team? Want to join a company that will invest in you? Learn more about joining our team. JOIN US OUR PARTNERSHIPS Our close partnerships with some of the industry's top performers will give you the best experience in using their groundbreaking, industry-defining tools and platforms. By keeping an open mind, a scientific curiosity, and an objective outlook, we accommodate and adapt our recommendations to the context of your business. LEARN MORE WHAT WE'RE UP TO NOW An Introduction to the World of Knowledge Graphs 174 Write a comment 5 NLP Introduction - How AI Understands Our Communication Patterns 169 Write a comment 6 Steps for a successful migration to Red Hat OpenShift Service on AWS (ROSA) 154 Write a comment View More WHAT PEOPLE SAY Media and Entertainment Software Provider We were impressed with Cedrus' ability and assets to support us during our Cloud migration. Cedrus is not a typical systems integrator- they understand the underlying business challenge and help resolve it through cutting edge technology practices. Their unparalleled expertise in implementing and deploying APIs/microservices to the Cloud enabled us to quickly and smoothly transition our software offerings to AWS. READY TO GET STARTED ? Get in touch with us! We're thrilled to answer your questions and help you define a vision. Contact Us

  • PCF to OpenShift Migration | Cedrus Digital

    Pivotal Cloud Foundry (PCF) to OpenShift Migration Cedrus can answer the key questions about Pivotal Cloud Foundry migration: how long will it take and how much will it cost? As experts in PCF as well as Kubernetes and OpenShift development, we have a low-risk, patterned approach from initial analysis through the actual migration. We can handle applications as simple as lift and shift or something as complex as re-engineering. Why migrate from PCF? Roadmap Product roadmap is unclear If you have to migrate, why not migrate to freedom? Kubernetes has a solid, clear direction forward Cost Kubernetes is free and open source Managed Kubernetes solutions are expanding and are cost-effective Capabilities Full-functional, secured, well-governed and mature platforms available such as OpenShift Kubernetes can fully manage persistence, allowing for stateful apps Portability Kubernetes is dominant and continues to improve rapidly Kubernetes apps and configuration can be easily moved between clusters/providers Kubernetes easily runs on VMs, Metal, and across IaaS providers Why Red Hat OpenShift? 1. Enterprise-ready PaaS functionality Your business is not platform building Outstanding dashboard and CLI to manage and monitor Deep integration with public clouds simplifies operations CI / CD built in - One line/page creation of apps from source to deployment Operator frameworks automate solutions Rich automation - for days 0, 1, and 2+ Built in image and operator repository 2. Security-first engineering No root usage in containers, RHEL / Fedora foundation S2I builds are better than Docker builds Strong RBAC isolation Built in adapters to connect to your identity provider(s) 3. Fully open source (Apache 2.0) OKD, the upstream version is available for free Why Cedrus? Over 20 years of experience in managing, architecting, and implementing successful platform migrations Dedicated Integration, Cloud, and Security practices Deep PCF experience Experienced Kubernetes team Red Hat Apex partner with expertise in Red Hat technologies including OpenShift, RHEL and Ansible Migration Methodology: 3 Phases Infrastructure / Platform Assessment and Implementation Enable visibility of legacy platform and all applications Identify and plan for all platform gaps and application dependencies Map functionalities to OpenShift early in the process CI / CD Pipeline Analysis and Implementation Validate the accuracy of your current pipeline process from a build, dev, release, prod, and validation perspective Adapt pipeline stages to leverage OpenShift standards like Helm and Operators Adapt pipeline stages to leverage OpenShift standards like Kubernetes Helm Charts and Operators Automated Code Migration Refactor the first application manually Produce code refactoring Run-Book Automate code refactoring for the rest of the applications Cedrus OpenShift Migration Tool The tool is a NodeJs , Yeoman generator that sums up the aspects, infrastructure needed and logistics of any application deployed on PCF in seconds. It scans the PCF platform through API's and the configuration files in the PCF applications against pre-defined and customizable rules. The customizable output provides an accurate summary for every application including details such as: Services in use Autoscaling Properties Instance profile (Dev, QA, Pre-Prod, Prod) Stack and Buildpack detail Shared Libraries summary Java and NGINX plugin and dependency details Customizable attributes as needed per unique migration PCF Migration - Journey to OpenShift and the Cloud WATCH PCF Migration Red Hat Webinar WATCH OpenShift and AWS blog READ WANT TO LEARN MORE ? Get in touch with us! We're thrilled to answer your questions and help you define a vision. Contact Us

View All