STAR Laboratory: SRILM Applications. SRILM is widely used in the research community for tasks requiring statistical language modeling. Below is a list of representative examples. Speech Recognition SRILM is used in SRI's commercial ASR engine DynaSpeak. SRILM has been used successfully with several freely available recognition systems, such as RWTH-ASR, Julius, Sphinx, and LIUM. SailAlign - a tool for robust long speech-text alignment Machine Translation LM support for the Moses SMT system. Tagging and Segmentation Document processing Outside Computational Linguistics Teaching IDEs and Language Bindings Please email webmaster@speech.sri.com webmaster<IMG SRC="/images/at.gif" ALT="*at*" ALIGN="BOTTOM">speech.sri.com to suggest additions to this page. SRILM is listed with the Natural Language Software Registry and with Language Technology World.
Back to SRILM main page. Registry. School of Informatics - Informatics Software Download Database. School of Informatics Software Download Database Welcome to the Informatics Software Download Database - a repository of the School of Informatics' software and data available for licensing and open source distribution. If you are looking for software, search by keyword (for example, "machine learning") or author below. If you are a staff member or student wishing to add your software to the repository, login here. You may search by keyword(s), author or both. Or browse the repository Top downloads 1SIMJAVA 2, downloads 24782HASE-III, downloads 22113WebExp2 1.3, downloads 16754RXP, downloads 15215AIAI Case - Based Reasoning Shell (Visual Basic Educational Version), downloads 1015 Recent uploads. Welcome to Language Technology World — LT World. Foundations of Statistical Natural Language Processing.
This is the companion website for the following book. Chris Manning and Hinrich Schütze, Foundations of Statistical Natural Language Processing, MIT Press. Cambridge, MA: May 1999. Interested in buying the book? Some more information about the book and sample chapters are available. If you are here to look up something that is mentioned in the book, click on the appropriate chapter link below. A list of errata is also available.
We'd be pleased to get feedback about how this book works out as a textbook, what is missing, or covered in too much detail, or what is simply wrong. Chapters Other resources Courses using the book Some courses that have used this book are the following (we're happy to be told of others!). UPenn CIS530, UPenn CIS639, Berkeley SIMS 296a-4, BYU CS479, Johns Hopkins: current (Eisner) and previous [lots of great slides by Jan Hajic!] Canada U Toronto CSC401, Concordia, Dalhousie U CSCI4152 [lots of slides!] Europe Middle East Asia. STAR Laboratory: SRI Language Modeling Toolkit. SRILM is a toolkit for building and applying statistical language models (LMs), primarily for use in speech recognition, statistical tagging and segmentation, and machine translation.
It has been under development in the SRI Speech Technology and Research Laboratory since 1995. The toolkit has also greatly benefitted from its use and enhancements during the Johns Hopkins University/CLSP summer workshops in 1995, 1996, 1997, and 2002 (see history). These pages and the software itself assume that you know what statistical language modeling is. To learn about language modeling we recommend the textbooks Either book gives an excellent introduction to N-gram language modeling, which is the main type of LM supported by SRILM. SRILM consists of the following components: A set of C++ class libraries implementing language models, supporting data stuctures and miscellaneous utility functions.
SRILM runs on UNIX and Windows platforms. Documentation SRILM is still under development. Terms of Use. SRI Speech: Products: Software Development Kits: EduSpeak. EduSpeak® The EduSpeak SDK is a speech recognition system for computer learning and training applications such as foreign language education, English as a second language (ESL), reading development and interactive tutoring, and corporate training and simulation. Access to its high-accuracy continuous speaker-independent speech recognition engine, is supported through several programming interfaces, such as Macromedia Director and Microsoft ActiveX, making it easy for developers of interactive, multimedia learning products to integrate voice input in their products.
For developers of computer-aided language learning and ESL products, SRI's patented pronunciation scoring technology provides feedback to language learners to help them compare how their spoken word or phrase pronunciation compares with that of a native speaker of the language they are learning. Features & Benefits Technical Specifications Download Size (Compressed): EduSpeak recognition engine: 0.6MB Acoustic model: 2.0MB.