You are here: silicon.com > Resources > White Papers > Software and Web Development > Software Development Tools > Voice Recognition

Voice Recognition White Papers

A Real-Time Japanese Broadcast News Closed-Captioning System

Overview This paper describes a collaboration between Bell Labs and NHK (Japan Broadcasting Corp.) STRL to develop a real-time large vocabulary speech recognition system for live closed-captioning of NHK news programs. Bell Labs broadcast news recognition engine consists of a two-pass decoder using bigram language models (LM) and right biphone models during the first pass, and trigram LM with within-word triphone models in the second pass. Various pruning strategies are used to achieve real time decoding, together with a noise compensation procedure aimed at improving recognition on noisy segments of the program.

Further White Paper Details
Publisher	Lucent Technologies	File Format	PDF, requires Acrobat Rdr 5
Date Published	June 2001	Downloads	4
Format	White Papers
Topics	Voice Recognition, Database Management

Did you find this white paper useful?

Speech recognition to become Nationwide security tool

After an infancy in the upper echelons of high-tech society, speech recognition has finally found its niche. Ironically, following a year of growing interest from consumers and small businesses, the biggest market for speech-recognition developer...

Channel:
Telecoms

Sci-fi or sci-future? Hollywood technology scrutinised (part two)

RK: We have speech recognition, language translation, and synthetic speech today. Computer speech recognisers are better than humans today on a word-by-word basis, but they lack cognition and contextualisation.

Channel:
Comment & Analysis

Lastminute.com launches speech recognition services

The service is based on VoiceXML and Lastminute.com is claiming this is the first consumer application to use both advanced speech recognition and text-to-speech technologies. Lastminute.com has launched a voice-automated service to let customers...

Channel:
Applications

Intel sets sights on lip-reading software

The Audio Visual Speech Recognition (AVSR) software tracks a speaker's face and mouth movements. By matching these movements with speech, the application can provide a computer with enough data to respond to voice recognition commands, even when...

Talking computers almost a reality

Yoda, a speech-to-text engine under development at Microsoft, can turn spoken word into coherent text email messages by studying a user's habits, said Alex Acero, manager of the speech research group at Microsoft.

Channel:
PDAs
Tags:
hal,
talking computers

Microsoft to buy speech-recognition web firm?

Microsoft is close to acquiring privately held Tellme Networks, a maker of products that bridge the worlds of speech recognition and the internet. The deal is expected to be completed and announced later this week, according to sources familiar...

Channel:
WebWatch
Tags:
tellme,
microsoft

Virtualisation: Architectual Considerations and other Evaluation Criteria

In the past several years, server virtualisation technology has moved quickly and firmly into the IT mainstream. Of the many approaches to system virtualisation available in the market today, VMware's hypervisor architecture has gained the greatest market acceptance. This paper examines the architectural issues, solution support, and enterprise readiness required when deploying such a virtualisation solution.

Publisher:
EMC

Getting Started with Master Data Management

Master data management forms part of an overall enterprise governance program that aims to establish trusted data throughout the enterprise. This white paper from Mike Ferguson of Intelligent Business Strategies defines master data, examines why it is needed, and explores methodologies for implementing master data management.

Publisher:
DataFlux

Optimising Storage with Global File Virtualisation

This white paper will provide an overview on how Rainfinity Global File Virtualisation virtualises unstructured data environments and moves data -including active, open files-without disruption to users or applications. Rainfinity is the only enterprise-class file virtualisation solution, and delivers complete NAS optimisation across geterogeneous environments, such as NAS, CAS, and file servers.

Publisher:
EMC

Also on silicon.com

Site Navigation:

Voice Recognition White Papers

A Real-Time Japanese Broadcast News Closed-Captioning System

Quick Sitemap Links:

About Us

Search

Blogs

Verticals

Advertising Features

CNET Networks in Europe

CNET Networks in the United States

CNET Networks in Asia Pacific