SpeechMax™

Add-On Advantages                 

More than a word processor™ A custom speech and text processor . . . .
Product Overview

What SpeechMax™ Can Do For You

 
Enter and Process Speech-Oriented Data

You Can Speak Faster than You Can Type

Imagine text processor, sound recorder, speech recognition or text to speech user interface, graphics and image display, web page and multimedia access, and data migration all in one application.    
Perform Multiple Speech-Oriented Tasks

Same Interface for All Users

Use for dictation, transcription, speech recognition, text to speech, forms creation and completion, presentations, document assembly, translation,  knowledge management, and other text and speech processing.
Run with Windows XP or Vista Compatible

Run as Standalone, on LAN, or Link to Web Services

Product may be used as standalone for home or small office, local area networked application, or linked to web services as add-on to information system, such as electronic medical record or personal health record. 
Read/Write Text, Audio, and Image Content

Document and Annotation Windows

The document may consist of text, audio, or images in the main document window, plus annotation window text or audio comments, hyperlinks, and multimedia linked to specific document text.  Data content may be displayed in many ways.
Utilize Unique Features

Many Patented or Patents Pending

Rapid "talking" forms creation and completion, audio-linked text for manual  transcription and speech recognition, autodetection speech recognition errors, speech and text redaction, scrambled session file, and session file lock. 
Who Is This Product For?

 

As a generic product, it can be used in health care, law, business, insurance, law enforcement, government, and education.  It has potential applications in the small office or large corporation or home.
View Session Data for Free

Full and FREE Reader Editions

The full edition includes all session read/write. The FREE Reader is a reader, viewer, and player for session content.  Displaying a locked session file, the Reader limits unauthorized editing of the portable session.
Key Features

More About  SpeechMax™

 
Create Speech-Oriented Session Data

Key Concept:  Text and Audio Annotations as Markup of Document Text

A "session" represents the sum of the data content of the document and annotation windows.  Use the document window for text or audio-linked text, images or graphics, and add markup through text or audio annotations.
Document Window

Click Audio-Linked Text For Playback

Document window supports read/write of RTF, TXT, HTML, or SES (session file). Select audio-linked text and playback the audio, or click highlighted document text to access text and audio annotations, hyperlinks, or multimedia.  
Session File (SES)

Create, Review, or Modify a "Session"

SpeechMax™ proprietary session file includes document window data content and associated annotations (comments).  Document window display uses HTML.  Underlying data content is stored as XML.
Multidocument Display

Display One, Ten, or More

Program supports opening two or more document windows (with annotations) simultaneously.  Document may be in same or different language.  User may tile windows vertically or horizontally, or as cascade.
Annotation Window

Create One or More Text or Audio Comments Linked to Document Text

The annotation window includes sound recorder, text box for text comments, list of parent and child annotations, annotation number, and execute button to access website or launch programs.   Programs may include media player and others.
Text Annotation

Dictate Directly into Document or Text Annotation with Speech Recognition

Each document window has its own annotation window for text comments for entry by keyboard, speech recognition, or bar code.  Any form of text data or comment may be included.  Unicode (multilingual) support is provided.
Copy Text Annotation

Move Annotation Text into Document Window to Edit Document or Complete Form

Annotation text may be transposed into the document window, moving the document text into annotation, or copied and pasted without transposition.  This supports document edit from the annotation window.
Verbatim Text

Create with Verbatim Annotation Feature
Verbatim text transcribed by court reporters indicates exactly what was said.  Distributed (final) text of a document or report may include editing.  With verbatim annotation, user can create audio-aligned verbatim record.  
Other Text Annotations

Link to a Website or Launch a Program

The annotation text can also link to a website or launch a program, e.g., a media player.  Use MultiLinksPRO™ to create links to more than one website associated to the same document text.  Provides a layered approach to references.
Audio Annotations

Can Also Move Audio Annotation into Document Window

Record audio comments or questions with built-in sound recorder, or by saving a prerecorded audio file.  As with text annotations, audio annotations are linked to specific text in the document window.  One or more annotations may be created for text.
Dictate Using Sound Recorder

Optional Copy Annotation Audio into Document Window and Link to Text

Use sound recorder to record dictation audio for manual transcription or speech recognition, enter comments, or dictate into form.  You can also dictate text with Dragon, IBM, Windows Vista, or other speech recognition
Text to Speech Audio Annotation Use the annotation window to create natural-sounding speech from AT&T Natural Voices and other text to speech programs as audio comments or prompts.  Voice fonts are available for different languages.  
Footpedal Support

Playback Document or Annotation Window Audio

Audio playback may be controlled with keyboard hotkeys.  The software also supports audio playback with a standard, off-the-shelf USB foot control.  No need for an expensive, proprietary device.   
Continuous or Segmental Playback Playback audio continuously, or advance to next phrase, or field in a form, and playback associated audio segment using keyboard hotkeys.  Footpedal also may be used for continuous or segmental playback. 
Audit Trail for Audio-Linked Text

Audio-Linked Text for Manual Transcription or Speech Recognition

With traditional manual transcription, the audio associated to a particular phrase cannot be located without playing back the audio file.  Use SpeechTracker™ to locate audio-linked segment from the verbatim or final text.
Speech Recognition Correction by An Assistant

A Better Way to Do Correction

With delegated correction, the editor can correct text, correct dictation errors (e.g., insert "left" for "right"), create headers and footers with transcription shell for completed document, and return for approval.  This saves the speaker time.
Multiple Popular Speech Engines Supported

Dragon, IBM, and Microsoft Vista

Correct a session file from real-time Dragon   speech recognition, a file transcribed with desktop Dragon or Microsoft Vista autotranscribe, or offline server-based speech recognition.  Potentially, other SAPI 5.x engines may be supported also.
Desktop Autotranscribe Autotranscribe of dictation audio file on desktop is available with Dragon or FREE Microsoft Vista speech recognition.  Microsoft autotranscribe application is available as a FREE SpeechMax™ add-on.
Manual Transcription Supported

Create Audio-Aligned Text

Autotranscribe tool may be used to segment dictation audio for manual transcription of an untranscribed session file.  The audio-aligned text may be used to create and train a speech recognition user.  
Advanced Error Spotting


Autodetection of Speech Recognition Errors
Spell check is commonly used in text processors, but speech recognition never makes a spelling mistake. Patented WordCheck™ text comparison identifies possible misrecognition errors, saving the editor time.
Color-Coding To Indicates Differences  WordCheck™ may be used in dual-window or multiwindow mode (view all compared documents) or single window mode.  Color coding may be used to indicate degree of differences with other documents.
Multilingual Document Creation Unicode enabled, each window can display English or a foreign language.  A single
document can also display more than one language character set. Enter characters with keyboard, speech recognition, or bar code.
Document Synchronization Documents with equal number of segments can be synchronized. Move the cursor in the index document and highlight corresponding segments in other documents. For example, use DataInSync™ to synchronize translations.
Censored (Redacted) Speech

Protect Confidentiality

With SpeechCensor™, remove document text or audio to deidentify patient or client name or other sensitive information. The audio is replaced by a "bleep," and the text is removed and replaced by "censored."  
Reordered (Scrambled) Utterances

Utterance Usually Represents Short Phrase Within Sentence--Dividing Speech at Natural Break Points

With ScrambledSpeech™, divide session file utterances into two or more bundles for transcription or edit.  You can also scramble utterances of each bundle, merging and unscrambling after processing.  
Speech Recognition Correction by Voice Using the audio annotation window, the same or different speaker can correct speech recognition text in the document window with voice, using the same or different speech engine.  Potentially, more than speaker can make the corrections.    
Redictation by Second Speaker

Decreased Corruption of Speech Files with a Dual Window Approach

Some transcriptionists or courtroom reporters use redictation to correct an original speaker's speech recognition text.  Corruption of speech user profile can be avoided by dictating corrections into the annotation window.
Image and Graphics Display

My AV Notebook™

For example, include images and graphics for an AV sales presentation with audio-linked text.  There are many other possibilities, such as electronic scrapbook, audio books, training manual, or lectures.  
Form Creation

The Talking Form™ -- You talk to it, and it talks to you™

SpeechMax™ supports creation of  "fill-in-the-blank" forms (templates).  Create audio prompts.  Complete the form with keyboard or traditional dictation, speech recognition, or bar code.   Forms may be used for structured dictation.
Navigation By Field An annotation name may correspond to a data field (e.g., "DOB" or "Name") in the form. Use a drop-down that displays field name or dictation options, and navigate directly to it using a dropdown or keyboard.
Structured Dictation Using The Talking Form™, it is easy to create dictation templates in a matter of minutes, without special programming or scripting.  These can be created for virtually any profession or business.   This allows saving data to searchable fields.
Document Assembly

Also For Collaborative Documents

Use text annotations to enter boilerplate options in a medical, legal, or other form.   Select text and assemble document by copying into document window.  May also be used for collaborative documents.
Knowledge Management By labeling phrases, sentences, and paragraphs with text annotation feature, these can be saved in searchable fields for future reference.  Create a database with language options, andIncorporate these variations into new documents.  
Portable Session File Using a graphical user interface or developer tools, Dragon, IBM, or Microsoft session file text or audio may be altered.  SessionLock™ limits unauthorized editing of session file content.  Use the Reader version to open the "portable" file.
SpeechMax™ as Process Component

Integrating SpeechMax™

 
Data Migration Prepopulate form data from another session file, comma-delimited file, XML file, or database.  You can also export data from the form.  Use the Data Migration Wizard to associate field content.  Migrate data to EMRs and other information systems.
Integrate with Microsoft Word SpeechMax™ Add-in to Word supports navigation within a form (template).  Dragon dictation into Word can also be edited in SpeechMax™ and corrections migrated back into the Word form.  This delegated correction saves the speaker time.
Speech and Language Training Data Verbatim text and audio may be used to train   acoustic and language models.  This data may be used for speech recognition for dictation, speaker ID, text to speech, machine translation, and language processing. 
Speaker-Specific Speech Recognition Using speaker-specific data from day-to-day transcription, a transcriptionist can create the user models for speaker-specific SweetSpeech™ speech recognition.  The user profile reflects speaker accent and background noise.
Semantic Processing Text annotation be used to associate dictated text with standardized terminologies, such as SNOMED in health care.  The standardized text may be stored as searchable fields in an EMR or other information system.  
Use Web Services Workflow and Telephone Dictation Server SpeechProfessional™ developer tools support integration with web-based workflow with server-based speech recognition and other back-end processingCommand!™ Call Center supports telephone dictation.
Integration Examples Company software has been integrated with health care, legal, insurance, and transcription company systems and many third-party products.  Integration has included HL-7 and other isystems.  See Case Studies.
Product Customization Services Services includes API modification, changing features or display, cobranding or rebranding with company name, splash screen, icon and link to customer website, and  translation of GUI to foreign language.  

       See for yourself--click here for video demos

 

Price, terms, specifications, and availability are subject to change without notice. Custom Speech USA, Inc. trademarks are indicated.   Other marks are the property of their respective owners.