Autonomy solutions enable live or recorded speech to be manipulated, edited, searched and automatically processed in the same way as text. This is achieved through SoftSound, renamed Virage SoftSound in 2007, which provides a wide range of speech-processing technologies, from audio segmentation and identification through to automatic speech recognition and understanding. SoftSound was founded in 1995 and is backed by over 10 years of research at Cambridge University.
Autonomy Virage Courtroom Transcription
Key features include:
State-of-the-art accuracy
Support of phonetics, word spotting and conceptual indexing and search
Highly scalable real-time recognition
Virtually unlimited vocabulary size
Industry-leading range of supported languages
Audio processing capabilities:
Speaker / audio segmentation
Speaker / audio classification
Identification of:
Topics being discussed
Genders of the speakers
Emotional character of speech
Amount and location of speech versus non-speech (e.g. background noise or silence)
Linguistic origin of speakers
Music
Audio Conceptual Tracking
A true industry first, Autonomy's Audio Conceptual Tracking tools allow users to analyze all the information held in rich media assets in a single view. Using significant breakthroughs in expectation maximization algorithms and usability modelling, Autonomy enables users to have access to all the concepts that are represented at different points in the audio stream, even as they are focusing on a particular point of a clip. This is a particularly empowering function since it allows users to work with rich media assets on a holistic basis rather than myopically on the segment they may be listening to.
Another important innovation and a true paradigm shifter, has been the ability for users to dynamically control the confidence of the speech recognition engine to match the business requirements per query. In traditional systems that deal with speech, the user typically must query what is essentially a black box for an answer and has no control over the confidence setting of the speech processing technology in use. For the first time, Autonomy allows end users to change the configuration of the speech recognition engine on the fly, per query, to suit their business needs. The higher the confidence setting, the lower the number of returned results but with fewer number of false positives.
In sum, the key features include:
Intelligent, concept-based marking of key ideas
Expansion of the concept viewer to encompass the entire asset in a single view, or focus on narrow parts of the asset
Summary: ...on finding innovative, cost-effective and practical approaches for delivering exceptional service to its clients. Recently, the firm became the latest organization to adopt matter-centric collaboration—a new paradigm for legal industry document management, pioneered by Interwoven—that combines state-of-the-art...
Summary: ...Sales and marketing • Customer satisfaction • Employee retention • Compliance • Coaching and training The Solution In 2006 Garlands installed Qfiniti Explore from Autonomy etalk, an interaction analytics technology solution that automates the understanding of speech from recorded customer-agent...
Summary: ...both enhance the customer experience and measure the resulting improvement in quality within the operation. Sky needed to implement a catalyst to change the way agents were assessed and managed, enabling true ownership of performance by the individual. Recommended Solutions Sky looked for a partner that...
Summary: ...Bristol Myers Squibb Case Study - Pharmaceutical Research and Development. Case Study Company Background With its unwavering commitment to the values of excellence, reliability, growth and innovation, BristolMyers Squibb is a true American success story. From humble beginnings in the latter half of the...
Summary: ...document store (archive) it is compressed for remarkable storage effi ciency. EAS also applies its SIS algorithm to ensure that only a single copy of the message is stored in the archive. Through data compression and true single instance storage, Equity One reduced the size of their information store...
Summary: ...Autonomy Case Study - Orange Telecom. • Equipment Releases/Issues – Speech analytics enables the business to retrieve agent/customer conversations with mentions of specific equipment (handsets) or issue types (such as defective batteries, accessories, etc.) • Coaching/Training – Speech analytics...
Summary: ...men’s 2-iron with a graphite shaft or a golf bag that costs less than $100. With IDOL K2, shoppers can quickly retrieve information for a specific model. IDOL K2 then allows shoppers to narrow their search to the most relevant categories—anything from Individual Irons, Iron Sets, and Wedges to Fairway...
Summary: ...Cardiff Case Study; American Express. [CDF AMX CS] www.cardiff.com way Linmar and (Cardiff) strove to address issues and improve capabilities.” For Mark King, senior manager, Customer Process Listening, the long-term success of the solution came from the constant commitment to improve the product. “TeleForm®...
Summary: ...including customers, employees, and suppliers, through a common, highly effcient Web content management infrastructure. Today, BT’s Interwoven-powered Web presence encompasses four lines of business—BT Global Services, Openreach, BT Retail and BT Wholesale—and handles millions of transactions per...
Summary: ...and markets of our clients with greater precision and at a fraction of the time as alternative technologies.” At a Glance Organization VMS Industry Media Type of Application Media Monitoring Autonomy Solution Intelligent Data Operating Layer Functionality Concept Retrieval Multimedia Search Hyperlinking...
Summary: ...This valuable integration enables TeleForm to automatically verify the customer warranty information captured from each card. TeleForm’s superior character recognition and data validation capabilities also help Bruno improve its service levels by significantly reducing the risk of data error and speeding...
Summary: ...case books. As they are completed, the pages are immediately faxed to Prologue where the data is passed from RightFax servers to the TeleForm optical character recognition engine. Once the data is “read” off the form, it gets transferred to the TeleForm Verifier queue for an operator to review. “Because...
This is a small selection of the Autonomy case studies available, please visit our publications site at http://publications.autonomy.com/ for more information.
Summary: ...media files based on the language spoken • Segmentation of speech sections based on the language spoken • Separation of speech from non-speech, including music, background noise, or silence • A high level of computational ef ficiency, which lowers overall operating costs Challenges and Methodology...
Summary: ...EDD and review of audio in-context with email and documents • Full suite of award-winning eDiscover y ser vices • Multiple speech analysis techniques for highest level of accuracy • Flexible, keyword, phoneme, and conceptual searching • Audio content redactions, produce redacted audio content...
Summary: ...of voice interactions. Autonomy’s speech recognition engine accounts for the variability in speech such as language, dialect, accent, or tone by using a speech recognition engine and advanced Meaning Based Computing to form an -hy pothesis of what is being said. Autonomy’s speech engine understands...
Summary: ...Recognition - Generates an index for any spoken content. • Sound Recognition - Recognizes specific audio such as applause, laughter, program jingles or tones. • Facial Recognition - Locates a face in the video, and matches facial features against a library of user-defined faces. • On-Screen Character...
Summary: ...market which allows users to search foreign multimedia in their native language, automatically generating real-time translations of audio streams and allowing users to compare content from around the world. The SoftSound Audio Analysis Plug-in detects speech and performs real-time speech-to-text transcription...
Summary: ...Autonomy Speech Analytics. Product Brief Highlights Meaning-Based Speech Recognition understands the concepts expressed in speech to determine topics, speakers, and emotions present in a voice interaction. • Processes real-time and recorded interactions, including pre-existing audio files from legacy...
Summary: ...responds to. With this information, the Segmentation & Targeting system then automatically targets the best content to each segment. Autonomy Optimosts’s segmentation automatically clusters site visitors based on any number of common characteristics, behaviors, and the content or concepts to which they...
Summary: ...analysis including speech-to-text, speaker identification, story recognition, name extraction and language translation Advanced video analysis including key framing, shot change detection, face recognition, logo detection and on-screen text recognition Automated clipping and segmentation with AutoClip™Identification...
Summary: ...adjustable keyframe sensitivity Media Analysis Plug-Ins: Standard or Advanced Speech Recognition for multiple languages Speaker Identification Audio Classification AutoClip Identification Face Recognition On-Screen Text Recognition SmartClips Name Extraction Automatic Translation Transcript Alignment...
Summary: ...speaker identification, story recognition, name extraction, and language translation Advanced video analysis including keyframing, shot change detection, face recognition, logo detection and on-screen text recognition Automated clipping and segmentation with AutoClip™ Identification and SmartClips™...
Summary: ...and topics of conversation in the call center • What other people are looking at – for example, the most popular or hottest related items • Conceptual interests – what key concepts they are reading or what videos they are watching • Sentiment – what they are saying in postings, ratings or...
This is a small selection of the Autonomy Product Briefs available, please visit our publications site at http://publications.autonomy.com/ for more information.
Summary: ...required by the user • Supports a virtually unlimited vocabulary size for an unrivalled range of single and multi-byte languages • Provides speaker and audio segmentation, speaker recognition and classification, and audio/text synchronization EAS and Autonomy ControlPoint for complete SharePoint governance...
Summary: ...make familiarity with the accents and special characters of different languages unnecessary. Canonicalization of characters Some encodings have more than one way of representing a character. The Japanese katakana script, for example, can be written in full width or half width characters. Regardless of...
Summary: ...Autonomy Document Management Server Technical Brief. Relevance Ranking In evaluating all types of queries, IDOL Server employs complex algorithms based on a combination of Information Theory and Bayesian methods to automatically weight and rank the document returns by statistical relevance. Automatic...
Summary: ...of IDOL modules (e.g. categorization, eduction, etc.) in the connector layer to further structure the ingested data during the importing process. Other benefits that Autonomy connectors provide include: • Comprehensive toolkit of parameterized filter operations, e.g. extract title • Create logical...
Summary: ...on a Domino Server or Notes Client for new documents to index into Autonomy IDOL server™. It can keep the Notes databases and IDOL server in sync so that deleted files are automatically removed from IDOL server and moved, modified or renamed file references are updated. Requirements Platforms Supported:...
Summary: ...another delivering the key benefits of using Autonomy's ACI (Autonomy Content Infrastructure) API or Simple Object Access Protocol (SOAP) enabled servers to facilitate interaction between Applications and Autonomy's Intelligent Data Operating Layer, and allowing simple manipulation of any returned result...
Summary: ...UNIX Code Traditional Chinese Extended UNIX Code Korean Extended UNIX Code Hebrew Hebrew (old) Pakistan (Urdu) Russian Adobe-Japan1-2 character collection Adobe-Korea1-0 character collection Adobe-GB1-3 character collection Adobe-CNS1-2 character collection ISO 2022-JP, Japanese mail and news safe encoding...
Summary: ...Santiago, Sao Paulo, Stockholm, Sydney, Tokyo, Utrecht and Washington, D.C. Features • Configurable aggregation of documents stored in FileNet • Configurable filtering of FileNet content based on standard and customizable fields, e.g. item types, file extensions • Accurate indexing in excess of...
This is a small selection of the Autonomy Technical Briefs available, please visit our publications site at http://publications.autonomy.com/ for more information.
Summary: ...in expectation maximization algorithms and usability modeling, Autonomy provides access to all the concepts that are represented at different points in the audio stream, even as a user is focusing on a particular point of a clip. This function allows users to work with rich media assets on a holistic...
Summary: ...spotting depends on high transcription accuracy, which is difficult given ambient background noise, and requires manipulation to account for multiple expressions of the same concept, such as the words “supervisor” and “manager”. In addition, these technologies lack the ability to correlate speech...
Summary: ...7 Speech Analytics Autonomy’s speaker-independent technology, based on superior speech processing algorithms, enables live or recorded speech to be manipulated, edited, searched, and hyperlinked as freely as text. It also develops a wide range of speech processing technologies, from audio segmentation...
Summary: ...Audio Recognition Virage Security and Surveillance speech recognition technology enables security organizations to search files in video, radio and telephony systems instantly. Virage’s speech technology is fundamentally different; whereas other technologies adopt a simple phonetic approach using only...
Summary: ...customer is on the phone. Speech recognition is an extremely di-f ficult task because of the variability of both speech and language; everyone sounds different, and there are nume-r ous ways to convey the same message in any language. Qfiniti Assist’s speech recognition engine accounts for this variability...
Summary: ...unstructured information. This is achieved through SoftSound Technology, a division of the Autonomy Group. SoftSound develops a wide range of speech processing technologies from audio segmentation and identification through to automatic speech recognition and understanding. Key Benefits • Reduce manual...
Summary: ...based on their spoken conversation. Speech recognition, however, is a difficult task because of the variability of both speech and language: everyone sounds different and there are numerous ways to convey the same message. Qfiniti Explore’s speech recognition engine accounts for this variability by...
Summary: ...acoustic models comprise both recurrent neural networks and hidden Markov models to obtain maximum speed and accuracy. These statistical models are made of every phoneme in the context of the preceding and following phoneme (e.g. the "a" sound is slightly different in "cat" than "nan"), so that they are...
Summary: ...could then be applied to other areas of the Website or other communications with customers. Website targeting has evolved to meet the challenge of the interactive marketer without the limitations imposed by black box solutions. True multivariable testing allows marketers to test virtually unlimited combinations...
Summary: ...of metadata and speech analytics. The voice masking solution can use any combination of time events, linguistic events, or activity events to define specific segments of the call to ‘mask’ out. A time event is the amount of time that has elapsed or is remaining in the call. A linguistic event is based...
Summary: ...the relevance of future documents. While most other models start with a prior knowledge of the state of the system and apply training to it, Autonomy begins with a blank slate and allows incoming data to dictate the model. In true Bayesian fashion, the model mixes new information with a growing body of...
Summary: ...thereby distinguishing homophones Use of both phonetic and conceptual approaches to offer unique high-level functions Audio, video, email and chat to be indexed and searched alongside other data formats Unrivalled accuracy by understanding words in context Speaker and audio segmentation, speaker recognition...
This is a small selection of the Autonomy White Papers available, please visit our publications site at http://publications.autonomy.com/ for more information.
Related Case Studies
.pdf.png)
.pdf.png)
.pdf.tiny.png)
