Search

Posted on cmajnews.com on May 8, 2019. Like many adult children of octogenarian parents, Edmonton entrepreneur Dave Damer takes every opportunity to accompany them on visits to the doctor. He [...]

In this paper we present two new techniques that have been used to build a large-vocabulary continuous Hindi speech recognition system. We present a technique for fast bootstrapping of initial phone models of a new language. The training data for the new language is aligned using an existing speech recognition engine for another language. This aligned data is used to obtain the initial acoustic models for the phones of the new language. Following this approach requires less training data. We also present a technique for generating baseforms (phonetic spellings) for phonetic languages such as Hindi. As is inherent in phonetic languages, rules generally capture the mapping of spelling to phonemes very well However, deep linguistic knowledge is required to write all possible rules, and there are some ambiguities in the language that are difficult to capture with rules. On the other hand, pure statistical techniques for baseform generation require large amounts of training data that are not readily available. We propose a hybrid approach that combines rule-based and statistical approaches in a two-step fashion. We evaluate the performance of the proposed approaches through various phonetic classification and recognition experiments.

Keep Ahead of the Technology Curve With this Special Report on Trends, Products, and Services That Are Just Around the Bend Even as you read this, manufacturers are putting the […]

Better automated acquisition of speech may be more about seeing than it is about hearing 'IF HE were proven to be malfunctioning, I wouldn't see how we'd have any choice [...]

Who are you calling emotional? Software that senses how you are feeling is being pitched to gadget-makers ON JANUARY 6th hordes will converge on a vast conference centre in Las [...]

Speech technologies offer call center managers important opportunities to improve customer satisfaction and reduce costs. According to industry analysts at Forrester, good speech-enabled phone self-service systems offer interaction advantages that […]

Byline: Amilda Dymi Nice Systems (NICE) in Ra'anana, Israel has developed voice recognition software that significantly reduces the time a call center employee needs to authenticate customers. The Nice Real-Time [...]

Once the ooing and ahhing about the Siri intelligent virtual assistant subsided a bit when the application appeared on Apple's (NASDAQ:AAPL) iPhone 4S in October, the tech press conjured questions [...]

Microsoft may have heavily touted its PC manufacturing partners' touch-screen technology at its recent Windows 7 launch, but the company is also exploring what it portrays as the next logical […]

In an effort to give its speech-recognition technology broader business application, Microsoft will stop selling its 2-year-old Speech Server software next year and fold its capabilities into an upcoming product […]

In an effort to improve the understanding of human speech patterns and early child development, a group of vendors is joining forces to test the scalability boundaries of storage by […]

Speech recognition company VoxGen and Vocability, the hosted speech services company, have developed a mobile karaoke application called Ring 'n' Sing that measures the pitch of a user's voice and […]

For some doctors, the prospect of trading in their paper-based patient files for electronic-medical-record systems means big changes in their work, and they and their staffs can't afford the initial […]

NEW YORK&#151On Wednesday, Microsoft Corp. took another step toward delivering its .Net platform that will allow developers, customers and integration partners to write and deploy speech-enabled applications and Web services. […]

Worldwide Computer Products News-2 October 2002-Aculab reveals its new biometric speech recognition software (C)1995-2002 M2 COMMUNICATIONS LTD http://www.m2.com Speech processing company Aculab is set to offer a speech verification and […]

Byline: Jim Barthold While there's certainly no such thing as free speech for prisoners and other criminal types under surveillance by various federal agencies, the difficulty of monitoring their phone [...]

While many speech technology companies have thrown their support behind the SALT Forum, VoiceXML remains their bread-and-butter speech platform, and they're closely watching efforts to integrate it with XHTML as […]

Clicking through multiple layers of menus and scrolling through tiny pages isn't the most efficient way to work with electronic information--just ask someone squinting at the screen of a personal […]

Domain Dynamics, signal processing and voice authentication specialist, has acquired ET Voice, the voice technology subsidiary of European Telecom plc, as part of its plan to become a leading global […]

An automated toolkit puts words in the mouths of virtual characters For many people, public speaking is a nightmare. Among those who are crippled by such exposure are animated characters. […]

COMPANIES SEEK WAYS FOR EMPLOYEES TO COMPLY WITH WIRELESS LAWS THE BAN ON TALKING ON CELL PHONES while driving in New York has spurred a flurry of activity among developers […]

2001: An ASP Odysseys With 2001 just around the corner, Reed Kingston says hosted speech recognition software is finally approaching the standards set by the HAL 9000, the murderous talking […]

Conventional wisdom says that voice recognition as an authentication mechanism for financial transactions is even further down the road than standardized e-signatures technology. But Veritel Corp. of America is banking […]

IMAGINE WALKING into your office and having your computer log on at your spoken command. That may be far from reality, but similar speech- recognition technologies are within three to […]

INTERNET BUSINESS NEWS-(C)1995-2000 M2 COMMUNICATIONS LTD The speech and language systems company Lernout & Hauspie Speech Products (L&H) has introduced an e-commerce portal for the provision of translation services. The […]

CORPORATE IT UPDATE-(C)1995-2000 M2 COMMUNICATIONS LTD SpeechWorks International Inc has introduced its new Speechify Text-to-Speech (TTS) technology, developed together with AT&T. According to SpeechWorks the new engine, which is designed […]

Conversational Computing Corp., a speech recognition software maker known as Conversa, this week will unveil its Conversation Server, a platform that provides a voice interface to networked content, including the […]

New concept adds real-time value to unified messaging. Unified communications services go beyond unified messaging, combining message exchange and other non-real-time activities with real-time communications, such as call delivery and […]

These e-commerce shopping agents are knowledgeable, patient, and affable during their conversational interaction with shoppers--while helping generate sales for site owners. CONSUMERS SPEND BILLIONS ONLINE, THOUGH MOST ARE UNHAPPY WITH […]

If you could speak to a computer that answers you in kind, or recogize you based solely on the properties of your voice,would you be happier with the interaction or […]

The latest moves in the voice recognition market have a lot of people talking. IBM last week announced new technology for adding voice recognition capabilities to PDAs, cell phones and […]

'The decline of america is dual to the automatic transmission home which actually came way back and go for the peace made a sleazy made us lazy. Modern poetry? Actually, […]

Deal Will Enable Users To Deploy Speech-Enabled Solutions That Blend Telephone, Fax, Email, Web Communications software and services provider Brooktrout Software is teaming up with SpeechWorks International Inc., a provider […]

* Philips has developed Speech Browser software (10Mb) that Lets you control Internet Explorer. The vocabulary is Web specialised and concentrates on expressions such as 'refresh' and 'go back'. The […]

Doing research on the internet has taken another step forward. Dragon Systems Inc. two weeks ago previewed its AudioMining speech technology, which will allow users to search and retrieve audio […]

Unisys Corp. and nuance communications, a maker of natural voice interface software, will announce this week an alliance to deliver speech recognition solutions to call centers and telecom service providers. […]