]> http://speechpro.com/ eng http://www.speechpro.com/comp-news/?action=show&id=104 Following the overwhelming success of the SpeechTEK event in the US, SpeechTEK Europe launches in London on 26 & 27 May 2010. SpeechTEK Europe will feature two packed days of conference sessions, keynotes and case studies plus an exhibit hall showcasing leading vendors and solutions providers, dedicated to bringing European buyers and sellers together in a focused setting. 07.05.2010 http://www.speechpro.com/comp-news/?action=show&id=102 The 1st EU–Russia Innovation Forum will be held on the 25 – 27th of May, 2010 in the City of Lappeenranta. The events will take place at the Lappeenranta City Hall and at the Lappeenranta University of Technology. 06.05.2010 http://www.speechpro.com/comp-news/?action=show&id=99 Speech Technology Center invites you to visit our booth at DSA 2010, which has now become one of the world's top 5 defense and security exhibitions and firmly remains the Asia Pacific region's most vital procurement hub for Defense and Security. 25.03.2010 http://www.speechpro.com/comp-news/?action=show&id=97 Speech Technology Center will take part and will hold an event sponsorship at the key industry event in the field of Voice Biometrics... 09.03.2010 http://www.speechpro.com/comp-news/?action=show&id=94 SpeechPro, the US branch of Speech Technology Center, invites to visit an Annual Winter Biometric Summit, which happens on February 22-25, 2010 in Miami. 17.02.2010 http://www.speechpro.com/comp-news/?action=show&id=93 Speech Technology Center invites you to view its exposition at CeBIT 2010, the world's foremost tradeshow for the digital industry. 17.02.2010 http://www.speechpro.com/comp-news/?action=show&id=92 Speech Technology Center invites you to visit our booth at ISS World MEA Dubai 2010 – the world's largest gathering of Middle East and African Law Enforcement, Intelligence and Homeland Security Analysts and Telecom Operators responsible for lawful interception, electronic investigations and network Intelligence gathering. 17.02.2010 http://www.speechpro.com/comp-news/?action=show&id=91 Speech Technology Center invites you to visit our booth at Defexpo India 2010. 12.02.2010 http://www.speechpro.com/comp-news/?action=show&id=86 FindBiometrics.com have published the Biometrics Review 2009 dedicated to key trends and events in Biometrics environment in 2009. 20.01.2010 http://www.speechpro.com/comp-news/?action=show&id=85 Speech Technology Center (STC) invites you to visit booth number 13H030 at the annual Milipol Paris 2009, Europe's largest military and police technologies exhibition that will take place in Paris, France on November 17, 2009 29.10.2009 http://www.speechpro.com/comp-news/?action=show&id=83 STC expert helped justifying Colombian Security Department.

In the course of audio examination the Key Expert of Speech Technology Center Sergey Koval has proved innocence of Colombian Administrative Department of Security (DAS) previously accused of illegal communications wiretapping. 07.10.2009 http://www.speechpro.com/comp-news/?action=show&id=82 Mikhail Khitrov CEO of Speech Technology Center takes part in international scientific conference InterSpeech held 6-10 September in Bighton (UK). 29.09.2009 http://www.speechpro.com/comp-news/?action=show&id=78 Speech Technology Center was the one and only Russian company to take part in SpeechTEK exhibition and conference (USA, NY). This largest speech technology event is organized in order to sum up the results of the current year and define the trends for the year to come. 11.09.2009 http://www.speechpro.com/comp-news/?action=show&id=77 Speech Technology Center is participating in SpeechTek’09 (New York City, Aug 24-26). 01.08.2009 http://www.speechpro.com/comp-news/?action=show&id=75 Speech Technology Center will be presented at Natia classes and exhibition. This event will take place at Memphis, on July 11-17, 2009. 10.07.2009 http://www.speechpro.com/comp-news/?action=show&id=74 Speech technology center was awarded as Russia’s best innovation company according to the results of the VIII “Russia’s innovations” contest organized by the “Expert” Media Holding and the State Youth Committee of the Russian Federation. 08.07.2009 http://www.speechpro.com/comp-news/?action=show&id=73 Arabic Interfaces for STC cutting-edge Audio Forensics and Voice Biometry software products made available. Speech Technology Center is honored to inform its customers and partners about the release of its Audio Forensics and Voice Biometry software applications with Arabic interfaces. 29.05.2009 http://www.speechpro.com/comp-news/?action=show&id=72 Lockheed Martin [NYSE: LMT] welcomed four industry leaders in vascular pattern, speaker and signature recognition technology at its Biometric Experimentation and Advanced Concepts (BEACON™) center in White Hall, WV, today. The BEACON is a collaborative space that brings industry, government and academia partners together to explore directions and advances in biometric technology. 05.05.2009 http://www.speechpro.com/comp-news/?action=show&id=71 Speech Technology Center will participate in “Biometrics on the Edge” Technology Forum on May 4, 2009 at the Lockheed Martin Biometrics Experimentation and Advanced Concepts (BEACON) in Whitehall, WV. 30.04.2009 http://www.speechpro.com/comp-news/?action=show&id=70 Speech Technology Center will take part at the first General Police Equipment Exhibition & Conference (GPEC). The conference will be held on June, 22-26 in Malaysian Putra World Trade Centre (PWTC). 17.04.2009 http://www.speechpro.com/comp-news/?action=show&id=69 The updated version of the professional audio analysis software SIS is released. The new SIS 7.x has extended capabilities and improved usability for audio examination. 03.04.2009 http://www.speechpro.com/comp-news/?action=show&id=67 Earlier this month STC has taken part in annual Call Center World Forum (CCWF) in Moscow. Today CCWF is one the most important events in the call-center industry not only in Russia but in whole Europe. 31.03.2009 http://www.speechpro.com/comp-news/?action=show&id=66 STC participated in the largest European IT exhibition CeBIT that took place 3-8 March 2009 in Hannover.This year STC presented at CeBIT two lines of products. First are the mobile solutions that include applications for voice biometrics, text-to-speech and command recognition. Second is VoiceNavigator that is a complete speech-driven IVR solution for call centers that include MRCP resources for speech recognition, text-to-speech and speaker verification by voice. 23.03.2009 http://www.speechpro.com/comp-news/?action=show&id=65 Speech Technology Center will participate in the “Telestrategies ISS World Europe” Conference that will take place 3-5 June, 2009 in Prague (Prague Congress Center). 12.03.2009 http://www.speechpro.com/comp-news/?action=show&id=64 The works on development of the sole product and its integration with Genesys Voice Platform (GVP) were being conducted during the last half a year. STC has developed the MRCP server with MRCPv1 and MRCPv2 support. 24.12.2008 http://www.speechpro.com/comp-news/?action=show&id=60 With over 100 specialists in its R&D team, speech database access a possible growth area Michael Khitrov, president, Speech Technology Center, was interviewed by Bill Meisel in late May. 19.11.2008 http://www.speechpro.com/comp-news/?action=show&id=59 STC Automatic speaker identification in forensics
at ISS World Europe
3-5 June, 2009
Prague, CZ 19.11.2008 http://www.speechpro.com/comp-news/?action=show&id=61 "One of the most effective software programs for detecting tampering is called Edit Tracker," said Tom Owen, president of Owl Investigations Services in Colonia, NJ. "The Russian scientist who originally developed it for the KGB brought it to market after the collapse of the Soviet Union. Edit Tracker analyses the recording for telltale signs of tampering, such as changes in background noise, artifacts left by stopping-and-starting recording, and a number of other 'signatures' that can be electronically detected." The results of Edit Tracker and other similar audio analysis programs are displayed graphically as waveforms, allowing investigators to actually "see" questionable sections of audio. 19.11.2008 http://www.speechpro.com/comp-news/?action=show&id=56 November, 17-19 Speech Technology center will participate at Milipol Qatar Exhibition at the new Qatar International Exhibition Center in Doha, booth D011 10.11.2008 http://www.speechpro.com/comp-news/?action=show&id=36 7 October three STC employees P.Zubova, S.Koval and I.Siparov were officially certified as forensic experts in voice biometrics by Federal Center of Forensics at Ministry of Justice, Russia. 27.10.2008 http://www.speechpro.com/comp-news/?action=show&id=35 This autumn STC will be represented at forthcoming scientific conferences IEEE Workshop on Spoken Language Technology and SLTC-2008. Papers on automatic speech synthesis and recognition will be published in the conference proceedings 23.10.2008 http://www.speechpro.com/comp-news/?action=show&id=53 In this paper, we are concerned with using decision trees (DT) and random forests (RF) in language modeling for Czech LVCSR. We show that the RF approach can be successfully implemented for language modeling of an inflectional language. Performance of word-based and morphological DTs and RFs was evaluated on lecture recognition task. We show that while DTs perform worse than conventional trigram language models (LM), RFs outperform the latter. WER (up to 3.4% relative) and perplexity (10%) reduction over the trigram model can be gained with morphological RFs. Further improvement is obtained after interpolation of DT and RF LMs with the trigram one (up to 15.6% perplexity and 4.8% WER relative reduction). In this paper we also investigate distribution of morphological feature types chosen for splitting data at different levels of DTs. 21.10.2008 http://www.speechpro.com/comp-news/?action=show&id=54 In this paper we show that the Random Forest (RF) approach can be successfully implemented for language modeling of an inflectional language for Automatic Speech Recognition (ASR) tasks. While Decision Trees (DTs) perform worse than a conventional trigram language model (LM), RFs outperform the latter. WER (up to 3.4% relative) and perplexity (10%) reduction over the trigram model can be gained with morphological RFs. Further improvement is obtained after interpolation of DT and RF LMs with the trigram one (up to 15.6% perplexity and 4.8% WER relative reduction).
÷èòàòü äàëåå 21.10.2008 http://www.speechpro.com/comp-news/?action=show&id=55 This paper outlines a project on the development of a new hybrid unit-selection and concatenative Russian TTS system. Project is held within Federal Research and Development Program in Priority Directions of Development of Scientific and Technological Complex of Russia in 2007-2012. A new generation Russian TTS that makes use of syntactic and semantic analysis and can be implemented in various types of electronic devices is the major aim of the project.
÷èòàòü äàëåå 20.10.2008 http://www.speechpro.com/comp-news/?action=show&id=34 Speech Technology Center will participate in the “Telestrategies ISS World Europe” Conference that will take place 1-3 October 2008 in Prague (Prague Congress Center). 20.09.2008 http://www.speechpro.com/comp-news/?action=show&id=33 The head of STC’s expert department Polina Zubova made a report about identification on a language unknown to an expert on the 10^th ENFSI FSAAWG conference that was hold in Bratislava, Slovakia, 11-12^th September. 18.09.2008 http://www.speechpro.com/comp-news/?action=show&id=32 Speech Technology Center invites you to visit Russian Innovations exhibition, Bangkok, 8-13 August 2008. You can find our booth in the Russian Federation Pavilion (BITEC, HALL 103) 07.08.2008 http://www.speechpro.com/comp-news/?action=show&id=31 Due to the successful partnership experience with Speech Technology Center General Sonora Prosecutor Office continues to equip the Forensic Audio Lab with the newest STC solutions. 24.07.2008 http://www.speechpro.com/comp-news/?action=show&id=62 Marisa T. Dery (Tamar Mastering, USA)  participated in the AES 33rd International Conference Denver, USA and won second place in the contest in audio enhancement.STC -a forensic software company from Russia-  was the winner of the contest. 15.07.2008 http://www.speechpro.com/comp-news/?action=show&id=30 The Russian Ministry of IT and Communications awarded St. Petersburg's Speech Technology Center (STC) the prize for corporate integration of modern information systems and technologies. STC won for its Quality Management System. 27.06.2008 http://www.speechpro.com/comp-news/?action=show&id=29 STC participated in the AES 33rd International Conference Denver, USA and won the contest in audio enhancement. 11.06.2008 http://www.speechpro.com/comp-news/?action=show&id=28 STC has released a crucially new version of the distributed speech transcription system “Nestor”. It enables simultaneous transcription of speeches, meetings, congresses, conferences of Executive, Legislative and Judicial Government Forces, Public and Business Entities. 06.06.2008 http://www.speechpro.com/comp-news/?action=show&id=27 STC successfully installed several sets of the Audio Forensic Laboratories at the Ministry of Interior of the Kingdom of Saudi Arabia. 16.05.2008 http://www.speechpro.com/comp-news/?action=show&id=26 The Federal Police of Argentina in cooperation with The Federal University of Argentina received equipment and successfully completed the course of Audio Forensic training by the Speech Technology Center. 13.05.2008 http://www.speechpro.com/comp-news/?action=show&id=25 Over 100 private and governmental audio examiners will come in Denver, CO to participate in the 33d AES Conference. The speeches of participants will be devoted to the current issues of audio authenticity, audio transcription and speaker identification. 22.04.2008 http://www.speechpro.com/comp-news/?action=show&id=24 Speech Technology Center will participate in the “Telestrategies ISS World Asia Pacific” Conference that will take place 09-11 June 2008 in Singapore. The event is dedicated to Intelligence Support Systems for Lawful Interception, Criminal Investigations and Intelligence Gathering and will be the world’s largest gathering of Telecom Operators, Law Enforcement, Interior Security and the Intelligence Community to learn and network. 18.04.2008 http://www.speechpro.com/comp-news/?action=show&id=23 Automatic Voice Search System Trawl-X has won the Golden Medal of the prestigious industrial award “ZUBR 2008” in the “Information Security” nomination. The committee marked that it is the first Russian automatic voice search system. 17.04.2008 http://www.speechpro.com/comp-news/?action=show&id=22 The Head of STC’s Training and Support department Zubova Polina has been admitted as a full member of the Audio Engineering Society. 10.04.2008 http://www.speechpro.com/comp-news/?action=show&id=21 Cnews magazine has placed "Speech Technology Center" in the ten of the abroad most known Russian IT companies. 04.04.2008 http://www.speechpro.com/comp-news/?action=show&id=20 SPEECH IS THE MOST NATURAL WAY TO COMMUNICATE! ISN’T IT?
Everything you always wanted to know about speech technologies you will find at CeBIT 2008 (Hannover - Germany, 4-9 March, Hall 6 stand G02). 19.02.2008 http://www.speechpro.com/comp-news/?action=show&id=18 St. Petersburg, Russia – St. Petersburg’s Speech Technology Centre (STC) has launched the RUSSOGRAGH, the first speech-to-text technology for continuous Russian speech. 08.02.2008 http://www.speechpro.com/comp-news/?action=show&id=19 A complete quality reaudit was performed in Speech Technology Center by the leading auditors of Det Norske Veritas Company to verify the effectiveness of international Quality Management System ISO 9001:2000 in January 2008. 08.02.2008 http://www.speechpro.com/comp-news/?action=show&id=17 “Speech Technology Center” and “Android Robotics Corp” have teamed up to create a new voice-operated robot. The presentation of the new humanoid robot has taken place in the Scientific Center of the JSC “Russian Railways” on the 20th of December, 2007. 21.12.2007 http://www.speechpro.com/comp-news/?action=show&id=16 December 3-8, 2007 STC with Owl Investigations, Inc. hold a seminar in Colonia, New Jersey, for USA private and state experts concerning application of professional software set IKAR LAB in audio/speech signal examination. 18.12.2007 http://www.speechpro.com/comp-news/?action=show&id=15 Owl Investigation, Inc holds a seminar on the usage of the forensic acoustic laboratory IKAR-LAB produced by STC. 28.11.2007 http://www.speechpro.com/comp-news/?action=show&id=14 November 18–21, 2007. Speech Technology Center has participated in the Russian National Exhibition in Johannesburg, South African Republic. 27.11.2007 http://www.speechpro.com/comp-news/?action=show&id=52 This paper outlines a recently started project on development of a new hybrid unit-selection and
concatenative Russian TTS system. Project is held within Federal Research and Development Program in Priority Directions of Development of Scientific and Technological Complex of Russia in 2007-20121 (http://www.fcntp.ru/). Major features of the proposed system are presented. Stimulating a wide scientific discussion that would help to improve the system at the
early stages is the main aim of the paper.
÷èòàòü äàëåå 18.10.2007 http://www.speechpro.com/comp-news/?action=show&id=50 The method for compensation of session variability in text-independent speaker verification is presented in this paper. It is based on maximum likelihood estimations for speaker sessions modelling. The method is shown to reduce the verification error by 21% for 4-second and by 36% for 20-second testing segments comparing to the GMM-UBM baseline. The evaluation was performed for conversational speech recorded in GSM channels.
÷èòàòü äàëåå 16.10.2007 http://www.speechpro.com/comp-news/?action=show&id=51 A formalized approach to pitch-based speaker discrimination using identical components of pitch contour structure is presented. The designed list of pitch units includes 7 basic unit types (16 subtypes). Each unit is described with a set of relevant pitch parameters. The effectiveness of three unit types (nuclear fall, nuclear rise and a filled hesitation pause) was tested on a 10-male speech corpus first on 2-session and 3-session data. The results show a positive discriminating potential of certain pitch parameters. The lowest EER values were obtained for the so-called “physical” F0 parameters of a rising nucleus (18% for F0 minimum in a 2-session comparison and 22% for F0 mean in a 3-session comparison). The fusion of all parameters for the three contour unit types produced an EER of 13% in a 3-session comparison.
÷èòàòü äàëåå 16.10.2007 http://www.speechpro.com/comp-news/?action=show&id=13 In the final of Russian Venture Forum held in St-Petersburg on October 10-12 Microsoft analysts awarded Speech Technology Center the winner in nomination «Software development: the brightest prospect». 16.10.2007 http://www.speechpro.com/comp-news/?action=show&id=49 Progress in the development of the Large Vocabulary Speech Recognition System created at Speech Technology Center is presented in this paper. The most widely used method for creating context-dependent phones is based on growing a decision tree with branches defined by binary questions, concerning neighbor phones. The list of questions may vary and is to some extent arbitrary. Decision on splitting is based on the behavior of entropy.
A new method based on recognition scores of phones is proposed. At each step of the algorithm additional models are introduced whenever existent models of monophones or triphones are poorly recognized. Retraining of the new model rearranges the training data between all models.
The problem of unseen triphones is solved by introducing a measure of similarity of contexts and
by clustering monophones according to this measure.
Context-dependent phones obtained with this method were tested on the task of keyword spotting. This limited task was chosen due to known and not properly solved problems concerned with creating decoder for LVCSR.
÷èòàòü äàëåå 15.10.2007 http://www.speechpro.com/comp-news/?action=show&id=12 We invite you to visit the booth of Speech Technology Center, Ltd. at the largest European exhibition of military and police technique Milipol Paris 2007. 19.09.2007 http://www.speechpro.com/comp-news/?action=show&id=11 6th-7th September, 2007, the 9th meeting of ENFSI Forensic Speech and Audio Analysis Expert Working Group (FSAAEWG) took place in Krakow, Poland. 11.09.2007 http://www.speechpro.com/comp-news/?action=show&id=10 XVI International Congress of Phonetic Sciences took place in Saarbrucken (Germany) 6-10 August. The congress is held every 4 years and it gathers leading specialists in the fields of phonetics and speech technology. 14.08.2007 http://www.speechpro.com/comp-news/?action=show&id=48 A method of selective pitch data comparison for speaker identification is presented. Pitch parameters of rising and falling nuclear monosyllables and filled hesitation pauses are evaluated for their discriminating ability using F-ratio and EER measures obtained on a 10-male 3-session speech database. “Physical” F0 parameters providing 20%- 30% EER in isolation proved more effective than linguistically conditioned ones. Using all parameters in combination produced an EER of 13%.
Directions of future research are outlined and the scope of possible method application in forensic tasks is scussed.
÷èòàòü äàëåå 10.08.2007 http://www.speechpro.com/comp-news/?action=show&id=9 Meet us at SpeechTEK East Exhibition and Conference (August 20-22, 2007, New York Marriot Marquis, NY, the USA)! Our booth number is 513. 06.07.2007 http://www.speechpro.com/comp-news/?action=show&id=40 This paper presents a physiologically inspired feature
extraction algorithm for employment within the speech
recognition engines, which are supposed to remain effective in noisy environments. Essentially, the algorithm simulates a key property of the “active cochlea” models – a signal dependent variable gain over the frequency range. In order to drastically reduce computational complexity of the algorithm in comparison to the original time domain “active cochlea” models, it is implemented in the frequency domain with the help of a warped discrete Fourier transformation (WDFT). The essence of FASM technique is that in the presence of the noise, higher frequency channels get more attenuation if there
are “enough” signal components in the lower, less susceptible to the noise influence, part of the spectrum. As it is confirmed by the performed measurements FASM algorithm allows to boost feature invariance to noise while keeping feature informativeness at the acceptable level.

read more... 29.06.2007 http://www.speechpro.com/comp-news/?action=show&id=38 Different types of acoustic models created at Speech
Technology Center are evaluated in this paper. Our main goal was to test how well those models work and choose one model for implementation in a large vocabulary continuous speech recognition (LVCSR) system for Russian which is under development now. Context-independent discrete and continuous models, as well as context-dependent continuous models, were built and evaluated on an isolated word recognition task. The results gained with the contextdep endent
continuous model prove its consistency and show it
can be used for acoustic modelling in a large vocabulary
speech recognizer.
read more... 29.06.2007 http://www.speechpro.com/comp-news/?action=show&id=37 Search engines such as Google are receiving about 1 billion search requests per day. Taking the ability to query text and applying it to voice opens up many areas of opportunity. As it pertains to the Web, users can search audio files and audiovideo feeds. Enterprises can use this technology to find important customer concerns and even potentially enable employees to search voicemails or recorded calls for key words and phrases. It would seem that the sky is the limit for this technology, which is why Speech Technology magazine pulled together a group of experts to determine the limitations and opportunities for the audio search and mining industry.
read more... 27.06.2007 http://www.speechpro.com/comp-news/?action=show&id=44 This paper introduces a linguistically motivated rule-based method of automatic segmentation of a Russian text in intonational units. We claim that it can provide a high correct prosodic break assignment rate (92.1% junctures correct for spontaneous speech), staying flexible at the same time, which is especially important for rule-based models. The kernel of the proposed algorithm, in addition to the use of punctuation, is automatic morphological analysis, which, being a complicated construct, is the base of a very simple interface grammar. This contextual grammar performs as an intermediate between a linguist and the core of the model, allowing the former to tune the whole system in a very efficient and intuitive way. The algorithm we present in this paper is implemented in the recent “Orator” text-to-speech system for Russian.

read more... 20.06.2007 http://www.speechpro.com/comp-news/?action=show&id=39 We analyse the properties of the physiological model of the adaptive behaviour of the chemical synapse between inner hair cells (IHC) and auditory neurons. On the basis of the performed analysis, we propose equivalent structures of the model for implementation in the digital domain. The main conclusion of the analysis is that the synapse reservoir model is equivalent in its properties to the signal-dependent automatic gain-control mechanism. We plot guidelines for creation of artificial anthropomorphic algorithms, which exploit properties of the original synapse model. This paper also presents a concise description of the experiments, which prove the presence of the positive effect from the introduction of the depicted anthropomorphic algorithm into feature extraction of the automated speech recognition engine.

Keywords and phrases: inner hair cell (IHC),Meddis IHC model, IHC adaptation, auditory models, modulation spectrum filtering.

read more... 02.06.2007 http://www.speechpro.com/comp-news/?action=show&id=8 STC presented it's new voice biometric database search system VoiceNet at VI AICEF (Academia Iberoamericana de Criminalistica y Estudios Forenses) Conference in Montevideo, Urugway on 16 of May, 2007. 21.05.2007 http://www.speechpro.com/comp-news/?action=show&id=42 Neuromorphic technology sets a goal of artificial recreation of the algorithms, which govern information processing in the live brain. The most vivid question here is a characterisation of the way real neurons relay information to each other. The present paper contains a concise description of a modelling approach aimed at quantification of the information transfer in the ascending auditory neural pass-ways.

read more... 14.05.2007 http://www.speechpro.com/comp-news/?action=show&id=46 This paper introduces a novel automatic speaker recognition system. The system includes a database of telephone speech templates and personal data for selected target speakers. The system performs noise cancellation and spectral normalization of the speech signal in the communication channel. Then automatic speech signal segmentation of the telephone conversation is performed to single out speech of a separate speaker. Having this speech sample a search is done over the database and an answer given how close this target speaker is to the known speakers. Speech spectral characteristics (formants) are compared. The reliability test gives 16% EER when both known and unknown speech samples are of 16 sec duration and 8% EER for 96 sec. The test was done on speech data of RUSTEN database (Russian telephone speech, 120 speakers * 5 sessions).
read more... 12.05.2007 http://www.speechpro.com/comp-news/?action=show&id=7 Earlier this month Julia Khitrova, STC`s VP Sales and Marketing, has represented STC at the 1st International Voice Biometrics Conference (Washington DC, U.S.A.). As the arrangers said in the opening address, the Conference calling was due to the necessity to determine the place and role for voiceprint technologies in modern biometric parameters row. 08.05.2007 http://www.speechpro.com/comp-news/?action=show&id=5 Earlier this week STC has successfully introduced itself at Hannover Messe, the world’s leading technology fair. In 2007 STC took part in this event for the first time at the joint booth of the Ministry of Science and Education of Russia. 23.04.2007 http://www.speechpro.com/comp-news/?action=show&id=6 On 24-27 April visitors of the 'Protection, Security & Fire Safety' Exhibition (MIPS) would have a great opportunity to see the latest achievements of STC in a field of CCTV and speech signal processing. Particularly, at the STC stand there will be presented Voice Digger software designed for key words spotting from phonograms in Russian. 23.04.2007 http://www.speechpro.com/comp-news/?action=show&id=43 This paper deals with the problem of pronunciation dictionary construction for large vocabulary continuous speech recognition (LVCSR). Here we present a method of constructing a stem-inflexion pronunciation vocabularies designed to use with a stem-based language model (LM) of Russian as an inflective language. We show that stem-based approach leads to 13 times reduction in the size of pronunciation vocabularies. On the base of this method we developed a tool called STcEM. STcEM was applied to several LVCSR tasks – to stemming of a free text and to the high-quality transcribing of stems and inflexions into monophones. We report here the results achieved while solving these two tasks. The related subtasks of context homography disambiguation, stress and ¸ place detection are discussed in details.

read more... 19.04.2007 http://www.speechpro.com/comp-news/?action=show&id=4 The world's leading trade fair for the IT and telecommunication industry CeBIT 2007 begins on the 15th of March in Hannover, Germany. Each spring, since 1986, CeBIT in Hanover brings under one roof over 6,200 exhibitors from around 70 countries and over 480,000 visitors from all over the world. 06.03.2007 http://www.speechpro.com/comp-news/?action=show&id=41 The technology for unlimited vocabulary automatic keyword spotting in spontaneous Russian speech is presented in this paper. We propose a novel speech database search system. It is based on the ideas of word pattern recognition and speech synthesis. Keywords to be searched are input in the text form and corresponding speech signals are synthesized by a text-tospeech (TTS) system. These signals are used as training material for a recognizer based on the dynamic programming approach. Evaluation of the system was performed for telephone and microphone channels. In the latter case, for a limited number of keywords searched simultaneously we gain
83% of hits without speaker adaptation (false alarm at 9.3%), and 99% of hits with speaker adaptation (17.5% of false alarms). Hit rate in noisy telephone channel is 78.5%, while false alarm rate is 60%.

read more... 02.03.2007 http://www.speechpro.com/comp-news/?action=show&id=3 SpeechTEK is a premier event where leading global companies meet. Speech Technology Center, the 1st Russian Speech Company, will be present at SpeechTEK this year to promote its unrivalled voice-driven solutions, and explore how STC can integrate speech technology in new products and services or deploy it. 19.02.2007 http://www.speechpro.com/comp-news/?action=show&id=45 Poor quality speech transcription is an everyday challenge in many applications, e.g. sound archives processing, forensic audio, etc. However speech intelligibility is often quite low due to noisy recording conditions or inadequate recording equipment performance. Moreover, usually it is impossible to get a new clearer recording or to enhance useful speech essentially. So listeners have to deal with degraded speech. This report describes some principles of noisy speech recordings processing for improvement of message intelligibility and quality and some methods to improve speech decoding speed and reliability. They are based on demasking and normalization of audio signals and on usage of binaural and adaptive properties of human hearing.
The discussed methods have a proven working track in STC and other services performing speech transcription by orders of courts, law enforcement, emergency and accident investigation services, etc.

read more... 07.02.2007 http://www.speechpro.com/comp-news/?action=show&id=2 The International Forum 'Security and Safety Technologies' (SST) is a leading security exhibition and congress event in Russia, CIS and Eastern Europe. Since 1996 Forum has been gathering more than 500 companies-participants from more than 20 countries and more than 28 thousand visitors from all around the world. 22.01.2007 http://www.speechpro.com/comp-news/?action=show&id=47 In this paper a new rule-based approach to break assignment for the Russian language is discussed. It is a flexible and robust method of segmentation of texts in Russian in prosodic units. We implemented it in the recent “Orator” text-to-speech (TTS) system. The model was
developed to use for the inflective languages as an alternative both for statistic and for strict rule-based algorithms. It is designed in such a way that all potentially tunable context dependencies are brought up to the
interface grammar and can be easily modified by linguists. The algorithm we developed performs well on different kinds of texts due to this simple and intuitive grammar built upon an elaborate mechanism of morphogrammatical
analysis. Juncture correct rate varies between more than
98% for simple literary texts and 85% for raw transcripts of spontaneous speech.

read more... 12.01.2007 http://www.speechpro.com/comp-news/?action=show&id=1 "Speech Technology Center" welcomes visitors of INTERPOLITEX-2006 - the 10th International Forum of Means for Provision of State Security and invites them to STC stand at Russian Exhibition Center, building 69, booth 1A-1.1 where our new products and solutions will be displayed on October 17-20. 19.09.2006 http://www.speechpro.com/comp-news/?action=show&id=63 Tom Owen (Owl Investigation) demonstrated STC software EdiTracker at 2006 AES/NY Picnic 13.06.2006 http://www.speechpro.com/comp-news/?action=show&id=105 Natia
Grapewine, USA 12.07.0110 http://www.speechpro.com/comp-news/?action=show&id=106 American Crime Laboratory Directors Symposium
Baltimor, USA 12.07.0110 http://www.speechpro.com/comp-news/?action=show&id=107 Biometrics Consortium Conference
Tampa, USA 12.07.0110 http://www.speechpro.com/comp-news/?action=show&id=108 Interspeech
Makuhari, Japan 12.07.0110