Foydalanuvchi:Wonmirzo/qumloq

Windows Speech Recognition
Ishlab chiquvchi	Microsoft
Chiqarilgan sana	30-noyabr, 2006-yil (2006-11-30)
Operatsion tizim	Windows Vista va undan keyingi versiyalar
Janr	Nutqni aniqlash

Windows Speech Recognition (WSR) – Microsoft tomonidan Windows Vista uchun ishlab chiqilgan nutqni aniqlash tizimi boʻlib, u ovozli buyruqlar yordamida ish stoli foydalanuvchi interfeysini boshqarish, elektron hujjatlar va elektron pochta matnini oʻqib berish, veb-saytlarda navigatsiya qilish, klaviatura qisqa buyruqlarini bajarish hamda sichqoncha kursorini boshqarish imkonini beradi. Bundan tashqari, tizim qoʻshimcha yoki yordamchi vazifalarni bajarish uchun moslashtirilgan makroslarni qoʻllab-quvvatlaydi.

WSR – lokal tarzda ishlaydigan nutqni aniqlash platformasi; aniqlik, matnni oʻqib berish yoki nutqni tanib olish uchun internetga yoki bulutli texnologiyalarga bogʻliq emas. Tizim kontekstlar, grammatikalar, nutq namunalariga moslashish, oʻquv mashgʻulotlari va lugʻatlar asosida ishlaydi. Foydalanuvchilar oʻzlariga xos lugʻat yaratishlari, unda kerakli soʻz va iboralarni qoʻshish yoki olib tashlashlari, hamda talaffuzlarni yozib olib, aniqlikni oshirishlari mumkin. Shuningdek, moslashtirilgan til modellari bilan ishlash imkoniyati ham mavjud.

WSR Windows tizimining ajralmas qismiga aylanishi uchun Windows Vista bilan birgalikda ishlab chiqilgan, chunki avval nutqni aniqlash texnologiyasi faqat Windows Media Player kabi maxsus dasturlarda boʻlgan. WSR texnologiyasi Windows 7, Windows 8, Windows 8.1, Windows RT, Windows 10 va Windows 11 operatsion tizimlarida ham mavjud. Windows Vista Betaʼning „Startup“ deb ataladigan versiyasi aslida nutqni aniqlash qoʻllanmasining boshlanishi boʻlgan va Windows XP tovushlaridan foydalangan.

Tarixi

Microsoft kompaniyasi WSR dan ancha avval nutqni aniqlash va ovozni sintez qilish sohasida koʻp yillik tadqiqotlar olib borgan. Microsoft 1993-yilda Carnegie Mellon Universitetidan Xuedong Huangni yollab, nutqni rivojlantirish loyihalarini boshqarishga tayinladi. Tadqiqotlar natijasida 1994-yilda Speech API (SAPI) ishlab chiqilgan va taqdim etilgan.

Masalan, Office XP va Office 2003 dasturlarida Internet Explorer va Microsoft Office ilovalari doirasida nutqni aniqlash funksiyalari mavjud edi. Shuningdek, Windows 98, Windows Me, Windows NT 4.0 va Windows 2000 operatsion tizimlarida cheklangan darajadagi ovozli boshqaruv funksiyalari taqdim etilgan edi. Windows XP Tablet PC Edition 2002 versiyasi nutqni aniqlash funksiyasini Tablet PC Input Panel orqali taqdim etdi va Windows XP uchun Microsoft Plus! ovozli buyruqlar yordamida Windows Media Player dasturida ovozli buyruqlar yoqildi.

Biroq, ushbu texnologiyalar alohida komponent sifatida oʻrnatilishni talab qilgan, chunki Windows Vistaʼga qadar Windows tizimida nutqni aniqlash keng qamrovli yoki integratsiyalashgan shaklda mavjud boʻlmagan. Office 2007 va undan keyingi versiyalar esa nutqni aniqlash uchun WSR’dan foydalanadi.

Windows Vista

2002-yilda oʻtkazilgan WinHEC konferensiyasida Microsoft Windows Vista (kod nomi: „Longhorn“) tizimida nutqni aniqlashdagi yangi yutuqlar va mikrofon massivlarini qoʻllab-quvvatlash kabi funksiyalarni joriy qilish rejasini eʼlon qildi. Bu yondashuv „tabiiy (uzluksiz) nutqni aniqlash va (diskret) buyruqlarni boshqarish uchun bir xil sifatli audio infratuzilmasini taʼminlash“ maqsadida amalga oshirilgan edi. 2003-yilgi PDC konferensiyasida Bill Geyts Microsoft tizimga nutqni aniqlash va ovozni sintez qilish imkoniyatlarini chuqur integratsiya qilishni rejalashtirayotganini va „Longhornʼda tanib olish va sintez qilishning real vaqt rejimida sezilarli rivoji“ni taʼminlashni maqsad qilganini taʼkidladi. Windows Vistaʼni ishlab chiqish jarayonida foydalanuvchini oʻqitish imkoniyatlariga ega nutq dvigateli dastlabki test versiyalarida mavjud edi. Shuningdek, foydalanuvchilar uchun mikrofon fikr-mulohazalari va boshqaruvi, shuningdek, foydalanuvchi sozlamalari va oʻquv imkoniyatlarini oʻz ichiga oladigan interfeys joriy etilishi rejalashtirilgan edi. Microsoft dasturiy ta’minotni ishlab chiqish to‘plamining dastlabki versiyasida menyular va tugmalar kabi umumiy nutq ssenariylarining tizim darajasida qoʻllab-quvvatlanishini eʼlon qilib, nutqni aniqlash qanchalik keng integratsiyalashganini tasdiqlagan edi.

2004-yilda oʻtkazilgan WinHEC konferensiyasida Microsoft WSR’ni mobil kompyuterlarda unumdorlikni oshirish strategiyasining bir qismi sifatida taqdim etdi. Keyinchalik, 2005-yilgi WinHEC konferensiyasida kompaniya nogironlik imkoniyatlarini kengaytirish, yangi mobil ssenariylarni qoʻllab-quvvatlash, qoʻshimcha tillar uchun yordam, va nutq bilan ishlash tajribasini yaxshilashni alohida taʼkidladi. Windows XP’dagi nutq qoʻllab-quvvatlashdan farqli oʻlaroq – u Tablet PC Input Panel bilan integratsiyalashgan va buyruqlar hamda diktant rejimlari oʻrtasida almashishni talab qilgan boʻlsa, Windows Vista ish stoli uchun nutq kiritishga bagʻishlangan maxsus interfeysni joriy qildi va alohida nutq rejimlarini birlashtirdi. Oldin foydalanuvchilar diktantdan keyin buyruq aytish yoki aksincha ishni bajarish uchun albatta rejimlarni oʻzgartirishi kerak edi. Windows Vista Beta 1 versiyasi nutqni aniqlashni tizimga integratsiyalashgan holda oʻz ichiga oldi. WSR’dagi xatoliklarni tahlil qilish va fikr-mulohazalarni taqdim etishni ragʻbatlantirish uchun Microsoft oʻz testchilari uchun Xbox 360 Premium modelini yutib olish imkoniyatini taklif qildi.

2006-yil 27-iyulda, Windows Vista ishlab chiqarishga chiqarilishidan (RTM) oldin Microsoft tomonidan oʻtkazilgan namoyishda WSR bilan bogʻliq eʼtiborga molik bir voqea sodir boʻldi. Nutqni diktant qilish boʻyicha bir necha marta urinishlar ketma-ket xatolarga olib kelib, kutilmagan holda „Aziz amma, keling, qotilni ikki barobar oshiraylik, oʻchirish, barchasini tanlash“ matnini chiqardi. Ushbu voqea tinglovchilar orasidagi tahlilchilar va jurnalistlar tomonidan keskin tanqidga uchradi, garchi dasturlarni boshqarish va navigatsiya boʻyicha boshqa bir namoyish muvaffaqiyatli oʻtgan boʻlsa ham. Microsoft ushbu muammolar nutqni tanib olish jarayonida audio signal kuchayishi bilan bogʻliq xato tufayli yuzaga kelganini aniqladi, bu esa buyruqlar va diktantlarning buzilishiga olib kelgan. Ushbu xatolik Windows Vista chiqarilishidan oldin tuzatildi.

2007-yil boshida WSR’da xavfsizlikka oid zaiflik aniqlangani haqida xabarlar tarqaldi. Ushbu zaiflik orqali tajovuzkorlar maqsadli qurilmada ovozli buyruqlarni dinamiklar orqali ijro etib, zararli operatsiyalarni amalga oshirishlari mumkin edi. Bu Windows Vista umumiy foydalanishga chiqarilgandan keyin aniqlangan birinchi zaiflik boʻldi. Microsoftning taʼkidlashicha, bunday hujum nazariy jihatdan mumkin boʻlsa-da, uning samaradorligini cheklaydigan yoki umuman oldini oladigan bir qator omillar va shartlar mavjud. Hujum amalga oshishi uchun, maqsadli qurilmada nutqni tanish funksiyasi faollashtirilgan va bunday buyruqlarni toʻgʻri talqin qiladigan darajada sozlangan boʻlishi kerak edi. Bundan tashqari, mikrofon va dinamiklar yoqilgan, ovoz balandligi esa yetarli darajada boʻlishi talab qilinardi. Shuningdek, hujum natijasida qurilma foydalanuvchining eʼtiborini tortuvchi koʻrinadigan operatsiyalarni bajarishi va eshitiladigan qayta aloqa signallari ishlab chiqarishi kerak edi, bu esa foydalanuvchining sezmasligi ehtimolini kamaytiradi. Foydalanuvchi hisobini boshqarish (User Account Control) esa yuqori darajadagi huquq talab qiladigan operatsiyalarning amalga oshirilishini toʻxtatib qoʻyardi.

Windows 7

WSR was updated to use Microsoft UI Automation and its engine now uses the WASAPI audio stack, substantially enhancing its performance and enabling support for echo cancellation, respectively. The document harvester, which can analyze and collect text in email and documents to contextualize user terms has improved performance, and now runs periodically in the background instead of only after recognizer startup. Sleep mode has also seen performance improvements and, to address security issues, the recognizer is turned off by default after users speak „stop listening“ instead of being suspended. Windows 7 also introduces an option to submit speech training data to Microsoft to improve future recognizer versions.

A new dictation scratchpad interface functions as a temporary document into which users can dictate or type text for insertion into applications that are not compatible with the Text Services Framework. Windows Vista previously provided an „enable dictation everywhere option“ for such applications.

Windows 8.x and Windows RT

WSR can be used to control the Metro user interface in Windows 8, Windows 8.1, and Windows RT with commands to open the Charms bar („Press Windows C“); to dictate or display commands in Metro-style apps („Press Windows Z“); to perform tasks in apps (e.g., „Change to Celsius“ in MSN Weather); and to display all installed apps listed by the Start screen („Apps“).

Windows 10

WSR is featured in the Settings application starting with the Windows 10 April 2018 Update (Version 1803); the change first appeared in Insider Preview Build 17083. The April 2018 Update also introduces a new Andoza:Keypress+Andoza:Keypress+Andoza:Keypress keyboard shortcut to activate WSR.

Windows 11

In Windows 11 version 22H2, a second Microsoft app, Voice Access, was added in addition to WSR. In December 2023 Microsoft announced that WSR is deprecated in favor of Voice Access and may be removed in a future build or release of Windows.

Overview and features

WSR allows a user to control applications and the Windows desktop user interface through voice commands. Users can dictate text within documents, email, and forms; control the operating system user interface; perform keyboard shortcuts; and move the mouse cursor. The majority of integrated applications in Windows Vista can be controlled; third-party applications must support the Text Services Framework for dictation. English (U. S.), English (U. K.), French, German, Japanese, Mandarin Chinese, and Spanish are supported languages.

When started for the first time, WSR presents a microphone setup wizard and an optional interactive step-by-step tutorial that users can commence to learn basic commands while adapting the recognizer to their specific voice characteristics; the tutorial is estimated to require approximately 10 minutes to complete. The accuracy of the recognizer increases through regular use, which adapts it to contexts, grammars, patterns, and vocabularies. Custom language models for the specific contexts, phonetics, and terminologies of users in particular occupational fields such as legal or medical are also supported. With Windows Search, the recognizer also can optionally harvest text in documents, email, as well as handwritten tablet PC input to contextualize and disambiguate terms to improve accuracy; no information is sent to Microsoft.

WSR is a locally processed speech recognition platform; it does not rely on cloud computing for accuracy, dictation, or recognition. Speech profiles that store information about users are retained locally. Backups and transfers of profiles can be performed via Windows Easy Transfer.

Interface

Fayl:WSRRecognizerStates.png

The speech recognizer displaying information based on different modes; the color of the recognizer button changes based on user interaction.

The WSR interface consists of a status area that displays instructions, information about commands (e.g., if a command is not heard by the recognizer), and the status of the recognizer; a voice meter displays visual feedback about volume levels. The status area represents the current state of WSR in a total of three modes, listed below with their respective meanings:

• Listening: The recognizer is active and waiting for user input
• Sleeping: The recognizer will not listen for or respond to commands other than „Start listening“
• Off: The recognizer will not listen or respond to any commands; this mode can be enabled by speaking „Stop listening“

Colors of the recognizer listening mode button denote its various modes of operation: blue when listening; blue-gray when sleeping; gray when turned off; and yellow when the user switches context (e.g., from the desktop to the taskbar) or when a voice command is misinterpreted. The status area can also display custom user information as part of Windows Speech Recognition Macros.

Fayl:WSR-AlternatesPanel.png

The alternates panel displaying suggestions for a phrase.

Alternates panel

An alternates panel disambiguation interface lists items interpreted as being relevant to a user’s spoken word(s); if the word or phrase that a user desired to insert into an application is listed among results, a user can speak the corresponding number of the word or phrase in the results and confirm this choice by speaking „OK“ to insert it within the application. The alternates panel also appear when launching applications or speaking commands that refer to more than one item (e.g., speaking „Start Internet Explorer“ may list both the web browser and a separate version with add-ons disabled). An ExactMatchOverPartialMatch entry in the Windows Registry can limit commands to items with exact names if there is more than one instance included in results.

Common commands

Listed below are common WSR commands. Words in italics indicate a word that can be substituted for the desired item (e.g., „direction“ in „scroll direction“ can be substituted with the word „down“). A „start typing“ command enables WSR to interpret all dictation commands as keyboard shortcuts.

Dictation commands: „New line“; „New paragraph“; „Tab“; „Literal word“; „Numeral number“; „Go to word“; „Go after word“; „No space“; „Go to start of sentence“; „Go to end of sentence“; „Go to start of paragraph“; „Go to end of paragraph“; „Go to start of document“ „Go to end of document“; „Go to field name“ (e.g., go to address, cc, or subject). Special characters such as a comma are dictated by speaking the name of the special character.

Navigation commands:

Keyboard shortcuts: „Press keyboard key“; „Press Andoza:Keypress plus Andoza:Keypress“; „Press capital Andoza:Keypress.“

Keys that can be pressed without first giving the press command include: Andoza:Keypress, Andoza:Keypress, Andoza:Keypress, Andoza:Keypress, Andoza:Keypress, Andoza:Keypress, Andoza:Keypress, and Andoza:Keypress.

Mouse commands: „Click“; „Click that“; „Double-click“; „Double-click that“; „Mark“; „Mark that“; „Right-click“; „Right-click that“; „MouseGrid“.

Window management commands: „Close (alternatively maximize, minimize, or restore) window“; „Close that“; „Close name of open application“; „Switch applications“; „Switch to name of open application“; „Scroll direction“; „Scroll direction in number of pages“; „Show desktop“; „Show Numbers.“

Speech recognition commands: „Start listening“; „Stop listening“; „Show speech options“; „Open speech dictionary“; „Move speech recognition“; „Minimize speech recognition“; „Restore speech recognition“. In the English language, applicable commands can be shown by speaking „What can I say?“ Users can also query the recognizer about tasks in Windows by speaking „How do I task name“ (e.g., „How do I install a printer?“) which opens related help documentation.

Fayl:Mousegrid.png

The MouseGrid command displaying a grid of numbers on the Windows Vista desktop.

MouseGrid

MouseGrid enables users to control the mouse cursor by overlaying numbers across nine regions on the screen; these regions gradually narrow as a user speaks the number(s) of the region on which to focus until the desired interface element is reached. Users can then issue commands including „Click number of region,“ which moves the mouse cursor to the desired region and then clicks it; and „Mark number of region“, which allows an item (such as a computer icon) in a region to be selected, which can then be clicked with the previous click command. Users also can interact with multiple regions at once.

Show Numbers

Applications and interface elements that do not present identifiable commands can still be controlled by asking the system to overlay numbers on top of them through a Show Numbers command. Once active, speaking the overlaid number selects that item so a user can open it or perform other operations. Show Numbers was designed so that users could interact with items that are not readily identifiable.

Fayl:Show numbers.png

The Show Numbers command overlaying numbers in the Games Explorer.

Dictation

WSR enables dictation of text in applications and Windows. If a dictation mistake occurs it can be corrected by speaking „Correct word“ or „Correct that“ and the alternates panel will appear and provide suggestions for correction; these suggestions can be selected by speaking the number corresponding to the number of the suggestion and by speaking „OK.“ If the desired item is not listed among suggestions, a user can speak it so that it might appear. Alternatively, users can speak „Spell it“ or „I’ll spell it myself“ to speak the desired word on letter-by-letter basis; users can use their personal alphabet or the NATO phonetic alphabet (e.g., „N as in November“) when spelling.

Multiple words in a sentence can be corrected simultaneously (for example, if a user speaks „dictating“ but the recognizer interprets this word as "the thing, " a user can state „correct the thing“ to correct both words at once). In the English language over 100,000 words are recognized by default.

Speech dictionary

A personal dictionary allows users to include or exclude certain words or expressions from dictation. When a user adds a word beginning with a capital letter to the dictionary, a user can specify whether it should always be capitalized or if capitalization depends on the context in which the word is spoken. Users can also record pronunciations for words added to the dictionary to increase recognition accuracy; words written via a stylus on a tablet PC for the Windows handwriting recognition feature are also stored. Information stored within a dictionary is included as part of a user’s speech profile. Users can open the speech dictionary by speaking the „show speech dictionary“ command.

Macros

Fayl:WSRMacroOptions.png

An Aero Wizard interface displaying options to create speech recognition macros.

WSR supports custom macros through a supplementary application by Microsoft that enables additional natural language commands. As an example of this functionality, an email macro released by Microsoft enables a natural language command where a user can speak „send email to contact about subject,“ which opens Microsoft Outlook to compose a new message with the designated contact and subject automatically inserted. Microsoft has also released sample macros for the speech dictionary, for Windows Media Player, for Microsoft PowerPoint, for speech synthesis, to switch between multiple microphones, to customize various aspects of audio device configuration such as volume levels, and for general natural language queries such as „What is the weather forecast?“ „What time is it?“ and „Whatʼs the date?“ Responses to these user inquiries are spoken back to the user in the active Microsoft text-to-speech voice installed on the machine.

Application or item	Sample macro phrases (italics indicate substitutable words)
Microsoft Outlook	Send email	Send email to	Send email to Makoto	Send email to Makoto Yamagishi	Send email to Makoto Yamagishi about	Send email to Makoto Yamagishi about This week’s meeting	Refresh Outlook email contacts
Microsoft PowerPoint	Next slide	Previous slide	Next	Previous	Go forward 5 slides	Go back 3 slides	Go to slide 8
Windows Media Player	Next track	Previous song	Play Beethoven	Play something by Mozart	Play the CD that has In the Hall of the Mountain King	Play something written in 1930	Pause music
Microphones in Windows	Microphone	Switch microphone	Microphone Array microphone	Switch to Line	Switch to Microphone Array	Switch to Line microphone	Switch to Microphone Array microphone
Volume levels in Windows	Mute the speakers	Unmute the speakers	Turn off the audio	Increase the volume	Increase the volume by 2 times	Decrease the volume by 50	Set the volume to 66
WSR Speech Dictionary	Export the speech dictionary	Add a pronunciation	Add that [selected text] to the speech dictionary	Block that [selected text] from the speech dictionary	Remove that [selected text]	[Selected text] sounds like…	What does that [selected text] sound like?
Speech Synthesis	Read that [selected text]	Read the next 3 paragraphs	Read the previous sentence	Please stop reading	What time is it?	Whatʼs today’s date?	Tell me the weather forecast for Redmond

Users and developers can create their own macros based on text transcription and substitution; application execution (with support for command-line arguments); keyboard shortcuts; emulation of existing voice commands; or a combination of these items. XML, JScript and VBScript are supported. Macros can be limited to specific applications and rules for macros can be defined programmatically. For a macro to load, it must be stored in a Speech Macros folder within the active user’s Documents directory. All macros are digitally signed by default if a user certificate is available to ensure that stored commands are not altered or loaded by third-parties; if a certificate is not available, an administrator can create one. Configurable security levels can prohibit unsigned macros from being loaded; to prompt users to sign macros after creation; and to load unsigned macros.

Performance

-Missing required parameter 1=''month''!, 2017-yil(2017-Missing required parameter 1=month!-00) holatiga koʻra WSR uses Microsoft Speech Recognizer 8.0, the version introduced in Windows Vista. For dictation it was found to be 93.6% accurate without training by Mark Hachman, a Senior Editor of PC World—a rate that is not as accurate as competing software. According to Microsoft, the rate of accuracy when trained is 99%. Hachman opined that Microsoft does not publicly discuss the feature because of the 2006 incident during the development of Windows Vista, with the result being that few users knew that documents could be dictated within Windows before the introduction of Cortana.

See also

• Braina
• List of speech recognition software
• Microsoft Cordless Phone System
• Microsoft Narrator
• Microsoft Voice Command
• Technical features new to Windows Vista

External links

• Windows Vista Speech Recognition demonstration at Microsoft Financial Analyst Meeting