![]() |
ISCApad #146 |
Tuesday, August 10, 2010 by Chris Wellekens |
5-1-1 | Automatic Speech and Speaker Recognition: Large Margin and Kernel Methods Automatic Speech and Speaker Recognition: Large Margin and Kernel Methods
Joseph Keshet and Samy Bengio, Editors
John Wiley & Sons
March, 2009
Website: Automatic Speech and Speaker Recognition: Large Margin and Kernel Methods
About the book:
This is the first book dedicated to uniting research related to speech and speaker recognition based on the recent advances in large margin and kernel methods. The first part of the book presents theoretical and practical foundations of large margin and kernel methods, from support vector machines to large margin methods for structured learning. The second part of the book is dedicated to acoustic modeling of continuous speech recognizers, where the grounds for practical large margin sequence learning are set. The third part introduces large margin methods for discriminative language modeling. The last part of the book is dedicated to the application of keyword-spotting, speaker
verification and spectral clustering.
Contributors: Yasemin Altun, Francis Bach, Samy Bengio, Dan Chazan, Koby Crammer, Mark Gales, Yves Grandvalet, David Grangier, Michael I. Jordan, Joseph Keshet, Johnny Mariéthoz, Lawrence Saul, Brian Roark, Fei Sha, Shai Shalev-Shwartz, Yoram Singer, and Nathan Srebo.
| |||||
5-1-2 | Some aspects of Speech and the Brain. Some aspects of Speech and the Brain.
Susanne Fuchs, Hélène Loevenbruck, Daniel Pape, Pascal Perrier
Editions Peter Lang, janvier 2009
What happens in the brain when humans are producing speech or when they are listening to it ? This is the main focus of the book, which includes a collection of 13 articles, written by researchers at some of the foremost European laboratories in the fields of linguistics, phonetics, psychology, cognitive sciences and neurosciences.
| |||||
5-1-3 | Spoken Language Processing Spoken Language Processing, edited by Joseph Mariani (IMMI and Publisher ISTE-Wiley Speech processing addresses various scientific and technological areas. It includes speech analysis and variable rate coding, in order to store or transmit speech. It also covers speech synthesis, especially from text, speech recognition, including speaker and language identification, and spoken language understanding. This book covers the following topics: how to realize speech production and perception systems, how to synthesize and understand speech using state-of-the-art methods in signal processing, pattern recognition, stochastic modeling, computational linguistics and human factor studies.
| |||||
5-1-4 | L'imagerie medicale pour l'etude de la parole Alain Marchal, Christian Cave Eds Hermes Lavoisier 99 euros • 304 pages • 16 x 24 • 2009 • ISBN : 978-2-7462-2235-9 Du miroir laryngé à la vidéofibroscopie actuelle, de la prise d'empreintes statiques à la palatographie dynamique, des débuts de la radiographie jusqu'à l'imagerie par résonance magnétique ou la magnétoencéphalographie, cet ouvrage passe en revue les différentes techniques d'imagerie utilisées pour étudier la parole tant du point de vue de la production que de celui de la perception. Les avantages et inconvénients ainsi que les limites de chaque technique sont passés en revue, tout en présentant les principaux résultats acquis avec chacune d'entre elles ainsi que leurs perspectives d'évolution. Écrit par des spécialistes soucieux d'être accessibles à un large public, cet ouvrage s'adresse à tous ceux qui étudient ou abordent la parole dans leurs activités professionnelles comme les phoniatres, ORL, orthophonistes et bien sûr les phonéticiens et les linguistes.
| |||||
5-1-5 | Korpusbasierte Sprachverarbeitung Author: Christoph Draxler
| |||||
5-1-6 | Linear Predictive Coding and the Internet Protocol, by Robert M. Gray Linear Predictive Coding and the Internet Protocol, by Robert M. Gray, a special edition hardback book from Foundations and Trends in Signal Processing (FnT SP). The book brings together two forthcoming issues of FnT SP, the first being a survey of LPC, the second a unique history of realtime digital speech on packet networks.
Volume 3, Issue 3 A Survey of Linear Predictive Coding: Part 1 of LPC and the IP By Robert M. Gray (Stanford University) http://www.nowpublishers.com/product.aspx?product=SIG&doi=2000000029
Volume 3, Issue 4
A History of Realtime Digital Speech on Packet Networks: Part 2 of LPC and the IP By Robert M. Gray (Stanford University) http://www.nowpublishers.com/product.aspx?product=SIG&doi=2000000036
The links above will take you to the article abstracts.
|
5-2-1 | ELRA Language Resources Catalogue Update (June 2010) ELRA is happy to announce that 2 new Speech Desktop/Microphone resources, 1 new Terminological Resource and 1 Written Corpus are now available in its catalogue: ELRA-S0305 EPAC Corpus: orthographic transcriptions
This corpus consists of approx. 100 hours of manual orthographic transcriptions, which were produced from 1,677 hours of non transcribed recordings from the ESTER Evaluation Campaign (Technolangue programme). This corpus also consists of automatic transcriptions of the full 1,677 hours.
For more information, see: http://catalog.elra.info/product_info.php?products_id=1119
ELRA-S0307 BABEL Polish database
The BABEL Polish Database is a speech database that was produced by a research consortium funded by the European Union under the COPERNICUS programme (COPERNICUS Project 1304). It consists of the basic 'common' set which contains the Many Talker Set (30 males, 30 females), the Few Talker Set (5 males, 5 females), the Very Few Talker Set (1 male, 1 female).
For more information, see: http://catalog.elra.info/product_info.php?products_id=1120
ELRA-T0374 Terminology database of natural sciences
This dictionary covers the three kingdoms: Animal, Vegetal, Mineral. It contains 50,000 species with numerous synonyms in French, English and Latin and many breeds and varieties. Minerals are given with their chemical formula. About 7,900 definitions in French are included. It also includes synonyms and linguistic variants.
For more information, see: http://catalog.elra.info/product_info.php?products_id=1121
ELRA-W0053 Catalan-Spanish Parallel Corpus
This corpus contains more than 100 million words and it contains 10 years of bilingual articles from “El Periódico de Catalunya”. The data are aligned at sentence level and stored in text files, in a one sentence per line basis. The data are provided in plain text, with no encoding whatsoever.
For more information, see: http://catalog.elra.info/product_info.php?products_id=1122
******
Moreover, please note that the content of the following 3 Terminological Resources has been updated and their prices have been revised:
ELRA-T0102 Terminology database of expressions
This resource comprises over about 26,000-30,000 expressions, such as sayings, proverbs, idioms, slogans, citations, exclamations, onomatopoeias and figurative expressions of French and English. Several grammatical topics that are included in some sentences are also handled. This resource contains synonyms. The DISCIPLINE field refers to the expression category: proverbs, idioms, postposition verbs.
For more information, see: http://catalog.elra.info/product_info.php?products_id=114
ELRA-T0103 Terminology database of finance
This dictionary covers the three kingdoms: Animal, Vegetal, Mineral. It contains 50,000 species with numerous synonyms in French, English and Latin and many breeds and varieties. Minerals are given with their chemical formula. About 7,900 definitions in French are included. It also includes synonyms and linguistic variants.
For more information, see: http://catalog.elra.info/product_info.php?products_id=115
ELRA-T0367 Terminology database of telecommunication
This resource comprises over 89,200 entries in the field of telecommunication. It also contains many synonyms and abbreviations in both languages, as well as meaning, case or applications for polysemic terms.
For more information, see: http://catalog.elra.info/product_info.php?products_id=659
For more information on the catalogue, please contact Valérie Mapelli mailto:mapelli@elda.org
Visit our On-line Catalogue: http://catalog.elra.info
Visit the Universal Catalogue: http://universal.elra.info
Archives of ELRA Language Resources Catalogue Updates: http://www.elra.info/LRs-Announcements.html
*****************************************************************
ELRA - Language Resources Catalogue - Update
*****************************************************************
In the framework of our ongoing campaign for updating and reducing the prices of the language resources distributed in the ELRA catalogue, ELRA is happy to announce that the prices for the following resources have been substantially reduced:
ELRA-S0074 British English SpeechDat(II) MDB-1000
This speech database contains the recordings of 1,000 British speakers recorded over the British mobile telephone network. Each speaker uttered around 40 read and spontaneous items.
For more information, see: http://catalog.elra.info/product_info.php?products_id=723
ELRA-S0075 Welsh SpeechDat(II) FDB-2000
This speech database contains the recordings of 2,000 Welsh speakers recorded over the British fixed telephone network. Each speaker uttered around 40 read and spontaneous items.
For more information, see: http://catalog.elra.info/product_info.php?products_id=557
ELRA-S0101 Spanish SpeechDat(II) FDB-1000
This speech database contains the recordings of 1,000 Castillan Spanish speakers recorded over the Spanish fixed telephone network. Each speaker uttered around 40 read and spontaneous items.
This database is a subset of the Spanish SpeechDat(II) FDB-4000 (ref. ELRA-S0102).
For more information, see: http://catalog.elra.info/product_info.php?products_id=726
ELRA-S0102 Spanish SpeechDat(II) FDB-4000
This speech database contains the recordings of 4,000 Castillan Spanish speakers recorded over the Spanish fixed telephone network. Each speaker uttered around 40 read and spontaneous items.
This database includes the Spanish SpeechDat(II) FDB-1000 (ref. ELRA-S0101).
For more information, see: http://catalog.elra.info/product_info.php?products_id=727
ELRA-S0140 Spanish SpeechDat-Car database
The Spanish SpeechDat-Car database contains the recordings in a car of 306 speakers, who uttered around 120 read and spontaneous items. Recordings have been made through 5 different channels, of which 4 were in-car microphones (1 close-talk microphone, 3 far-talk microphones) and 1 channel over the GSM network.
For more information, see: http://catalog.elra.info/product_info.php?products_id=690
ELRA-S0141 SALA Spanish Venezuelan Database
This speech database contains the recordings of 1,000 Venezuelan speakers recorded over the Venezuelan fixed telephone network. Each speaker uttered around 50 read and spontaneous items.
For more information, see: http://catalog.elra.info/product_info.php?products_id=736
ELRA-S0297 Hungarian Speecon database
The Hungarian Speecon database comprises the recordings of 555 adult Hungarian speakers and 50 child Hungarian speakers who uttered respectively over 290 items and 210 items (read and spontaneous).
For more information, see: http://catalog.elra.info/product_info.php?products_id=1094
ELRA-S0298 Czech Speecon database
The Czech Speecon database comprises the recordings of 550 adult Czech speakers and 50 child Czech speakers who uttered respectively over 290 items and 210 items (read and spontaneous).
For more information, see: http://catalog.elra.info/product_info.php?products_id=1095
For more information on the catalogue, please contact Valérie Mapelli mailto:mapelli@elda.org
Visit our On-line Catalogue: http://catalog.elra.info
Visit the Universal Catalogue: http://universal.elra.info
Archives of ELRA Language Resources Catalogue Updates: http://www.elra.info/LRs-Announcements.html
| |||||
5-2-2 | French corpus available Nous sommes heureux de vous annoncer la mise en ligne de C-Prom, un corpus de parole en français, en libre accès: http://sites.google.com/site/corpusprom Ce corpus est distribué librement à la communauté scientifique, sous licence CreativeCommons. Nous souhaitons qu'il puisse donner lieu à des études variées permettant aux chercheurs de confronter leurs analyses et d'éprouver leurs méthodologies sur un matériel partagé. Il est ouvert à des extensions d'enregistrements et d'annotations qui seront intégrées au fur et à mesure des contributions de tous.
Dans l'attente de vos visites et commentaires, nous vous adressons nos cordiales salutations,
Anne Catherine Simon (UCLouvain), Jean-Philippe Goldman (UniGe),
Mathieu Avanzi (UniNe, Paris 10, UCLouvain), Antoine Auchlin (UniGe)
| |||||
5-2-3 | LDC News In this newsletter: - Updated LDC Data Sheets and Papers Pages - New publications: - LDC Standard Arabic Morphological Analyzer (SAMA) Version 3.1 - - NIST 2004 Open Machine Translation (OpenMT) Evaluation -
Membership Year (MY) 2010 has included a strong selection of publications including updates to the Arabic and Chinese treebanks, Spanish telephone speech and transcript data from the Fisher collection, and Chinese word n-grams collected from the web . Please consult our corpus catalog for a full list of publications distributed by LDC. As we are now in the second half of this membership year, we would like to provide information on what publications you can expect for the remainder of MY2010. Our pipeline includes the following: Arabic Treebank Part 1 Version 4.1 ~ a revision of Arabic Treebank: Part 1 v 3.0 (POS with full vocalization + syntactic analysis) (LDC2005T02) (ATB1), according to the new Arabic Treebank (ATB) annotation guidelines. The Arabic Treebank project consists of two distinct phases: (a) Part-of-Speech (POS) tagging which divides the text into lexical tokens, and gives relevant information about each token such as lexical category, inflectional features, and a gloss, and (b) Arabic Treebanking which characterizes the constituent structures of word sequences, provides categories for each non-terminal node, and identifies null elements, co-reference, traces, etc. on-terminal node. Arabic Treebank Part 1 Version 4.1 represents the manual revision of the syntactic tree annotation in ATB1, the automatic revision and updating of certain part-of-speech tags, and the manual revision of certain targeted POS tags (function words, in particular). The source data consists of 734 newswire stories from Agence France Presse. Microsoft Research India POS-Tagged Bengali - to support the task of Part-of-Speech Tagging (POS) and other forms of data-driven linguistic research on Indian languages in general, Microsoft Research India has developed POS labeled data for Hindi, Bengali, and Sanskrit as a part of the Indian Language – Part-of-Speech Tagset (IL-POST) project. The corpora are based on the IL-POST framework. IL-POST is a POS-tagset framework which has been designed to cover the morph-syntactic details of Indian languages. It supports a three-level hierarchy of Categories, Types and Attributes. The Bengali corpus consists of two different levels of information for each lexical token: (a) lexical category and types, and (b) set morphological attributes and their associated values in the context. The data consists of 7168 manually annotated sentences (102933 words) targeted to cover written modern standard Bengali from various sources, including blogs, Multikulti, and Wikipedia. . TRECVID 2006 Keyframes and Transcripts ~ TREC Video Retrieval Evaluation (TRECVID) is sponsored by NIST to promote progress in content-based retrieval from digital video via open, metrics-based evaluation. The keyframes in this release were extracted for use in the NIST TRECVID 2006 Evaluation. The source data includes approximately 158.6 hours of English, Arabic and Chinese language video data collected by LDC from NBC, CNN, MSN, New Tang Dynasty TV, Phoenix TV, Lebanese Broadcasting Corp., and China Central TV. The keyframes were selected by going to the middle frame of the shot boundary, then parsing left and right of that frame to locate the nearest I-Frame. This then became the keyframe and was extracted. Keyframes have been provided at both the subshot (NRKF) and master shot (RKF) levels. Uda Walawe Asian Elephant Vocalizations ~ partially-annotated corpus of Asian Elephant communication/vocalization. The data set contains vocalizations primarily by adult female and juvenile Asian elephants. This corpus is intended to enable researchers in acoustic communication of elephants and other species to compare acoustic features and repertoire diversity to this population. Of particular interest is whether there may be regional dialects that differ among Asian elephant populations in the wild and in captivity. A second interest is in whether structural commonalities exist between this and other species that shed light on underlying social and ecological factors shaping communication systems. 2010 Subscription Members are automatically sent all MY2010 data as it is released. 2010 Standard Members are entitled to request 16 corpora for free from MY2010. Non-members may license most data for research use. [ top ] Updated LDC Data Sheets and Papers Pages LDC is pleased to announce that both our LDC Data Sheets and LDC Papers pages recently have been updated. On our Data Sheets page, you'll find our growing collection of LDC Data Sheets, each of which highlights a key aspect of the Consortium’s research and development tasks. Recent additions include a data sheet covering Arabic and English treebanking at LDC and one that provides an overview of LDC's role in sponsored projects. Our updated papers page contains several papers from LREC2010: Seventh International Conference on Language Resources and Evaluation, as well as other conferences and journals, dating from 1998 forward. Most papers are available for download in pdf format; presentations slides and posters are available for several papers as well. New Publications (1) The LDC Standard Arabic Morphological Analyzer (SAMA) Version 3.1 was developed by researchers at LDC. SAMA 3.1 is based on, and updates Tim Buckwalter's Buckwalter Arabic Morphological Analyzer (BAMA) 2.0 (LDC2004L02). Since this is the first public release of SAMA, it has been numbered continuously to reflect the continuity between this release and previous BAMA releases. SAMA 3.1 is a software tool for the morphological analysis of Standard Arabic. SAMA 3.1 considers each Arabic word token in all possible 'prefix-stem-suffix' segmentations, and lists all known/possible annotation solutions, with assignment of all diacritic marks, morpheme boundaries (separating clitics and inflectional morphemes from stems), and all Part-of-Speech (POS) labels and glosses for each morpheme segment. The generated output may then be reviewed by users, and the most appropriate annotation selected from among several choices. The software layer of SAMA 3.1 relies on a data layer that consists primarily of three Arabic-English lexicon files: prefixes (1328 entries), suffixes (945 entries), and stems (79318 entries representing 40654 lemmas). The lexicons are supplemented by three morphological compatibility tables used for controlling prefix-stem combinations (2497 entries), stem-suffix combinations (1632 entries), and prefix-suffix combinations (1180 entries). The input format, output format, and data layer of SAMA 3.1 were designed to be backward compatible with BAMA. Incremental changes to the data layer in SAMA have resulted in:
The software implementation has been updated to allow more input/output options, installation and configuration options, and smoother incorporation in other Perl tools/services. The structure of the dictionary and morphotactic tables has remained the same (the tables provided with SAMA 3.1 differ from the BAMA 2.0 tables only in size and content, not in format). Logical separation between the software layer and data layer allows the new software tools to be used with previous versions of the tables (instructions are provided with software documentation). The basic logic that implements the segmentation and analysis look-up for Arabic words is essentially unchanged since BAMA 2.0. The data layer is now accessed through Berkeley DB, with result-caching enabled by default, leading to improved performance. Various utility scripts have also been added to the software package to facilitate more flexible interaction with tools and data. LDC Standard Arabic Morphological Analyzer (SAMA) Version 3.1 is distributed via web download. 2010 Subscription Members will automatically receive two copies of this corpus on disc, provided that they have submitted a completed copy of the User License Agreement for LDC Standard Arabic Morphological Analyzer (SAMA) Version 3.1 (LDC2010L01). 2010 Standard Members may request a copy as part of their 16 free membership corpora. As a Members-Only release, LDC Standard Arabic Morphological Analyzer (SAMA) Version 3.1 is not available for non-member licensing. [ top ] (2) NIST 2004 Open Machine Translation (OpenMT) Evaluation is a package containing source data, reference translations, and scoring software used in the NIST 2004 OpenMT evaluation. It is designed to help evaluate the effectiveness of machine translation systems. The package was compiled and scoring software was developed by researchers at NIST, making use of newswire source data and reference translations collected and developed by LDC. The objective of the NIST OpenMT evaluation series is to support research in, and help advance the state of the art of, machine translation (MT) technologies -- technologies that translate text between human languages. Input may include all forms of text. The goal is for the output to be an adequate and fluent translation of the original. The 2004 task was to evaluate translation from Chinese to English and from Arabic to English. Additional information about these evaluations may be found at the NIST Open Machine Translation (OpenMT) Evaluation web site. This evaluation kit includes a single perl script (mteval-v11a.pl) that may be used to produce a translation quality score for one (or more) MT systems. The script works by comparing the system output translation with a set of (expert) reference translations of the same source text. Comparison is based on finding sequences of words in the reference translations that match word sequences in the system output translation. This corpus consists of 150 Arabic newswire documents, 150 Chinese newswire documents, and 29 Chinese 'prepared speech' documents. For each language, the test set consists of two files: a source and a reference file. Each reference file contains four independent translations of the data set. The evaluation year, source language, test set, version of the data, and source vs. reference file are reflected in the file name. NIST 2004 Open Machine Translation (OpenMT) Evaluation is distributed via web download. 2010 Subscription Members will automatically receive two copies of this corpus on disc. 2010 Standard Members may request a copy as part of their 16 free membership corpora. Non-members may license this data for US$150. [ top ]
|