1 |
Detailed Phonetic Labeling of Multi-language Database for Spoken Language Processing Applications
|
|
|
|
In: DTIC (2015)
|
|
BASE
|
|
Show details
|
|
2 |
Open-Source Multi-Language Audio Database for Spoken Language Processing Applications
|
|
|
|
In: DTIC (2012)
|
|
BASE
|
|
Show details
|
|
3 |
Advanced Subspace Techniques for Modeling Channel and Session Variability in a Speaker Recognition System
|
|
|
|
In: DTIC (2012)
|
|
BASE
|
|
Show details
|
|
4 |
Long Term Examination of Intra-Session and Inter-Session Speaker Variability
|
|
|
|
In: DTIC (2009)
|
|
BASE
|
|
Show details
|
|
5 |
Multilingual Phoneme Models for Rapid Speech Processing System Development
|
|
|
|
In: DTIC (2006)
|
|
Abstract:
Current speech recognition systems tend to be developed only for commercially viable languages. The resources needed for a typical speech recognition system include hundreds of hours of transcribed speech for acoustic models and 10 to 100 million words of text for language models; both of these requirements can be costly in time and money. The goal of this research is to facilitate rapid development of speech systems to new languages by using multilingual phoneme models to alleviate requirements for large amounts of transcribed speech. The Global Phone database, winch contains transcribed speech from 15 languages, is used as source data to derive multilingual phoneme models. Various bootstrapping processes arc used to develop an Arabic speech recognition system starting from monolingual English models, International Phonetic Association (IP based multilingual models, and data-driven multilingual models. The Kullback-Leibler distortion measure is used to derive data-driven phoneme clusters. It was found that multilingual bootstrapping methods outperform monolingual English bootstrapping methods on the Arabic evaluation data initially, and after three iterations of bootstrapping all systems show similar performance levels ; The original document contains color images.
|
|
Keyword:
*LANGUAGE; *SPEECH RECOGNITION; ACOUSTICS; CROSS-LANGUAGE; DATA BASES; DATA PROCESSING; ENGLISH LANGUAGE; HIDDEN MARKOV MODELS; INTERNATIONAL; ITERATIONS; MODELS; MULTILINGUAL; PHONETICS; SOURCES; SPEECH; VIABILITY; Voice Communications; WINCHES
|
|
URL: http://www.dtic.mil/docs/citations/ADA457034 http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA457034
|
|
BASE
|
|
Hide details
|
|
6 |
Performance Assessment of Dynaspeak Speech Recognition System on Inflight Databases
|
|
|
|
In: DTIC AND NTIS (2004)
|
|
BASE
|
|
Show details
|
|
7 |
Implications of Multilingual Interoperability of Speech Technology for Military Use (Les implications de l'interoperabilite multilingue des technologies vocales pour applications militaires)
|
|
|
|
In: DTIC AND NTIS (2004)
|
|
BASE
|
|
Show details
|
|
8 |
Implications of Multilingual Interoperability of Speech Technology for Military Use (Les implications de l'interoperabilite multilingue des technologies vocales pour applications militaires) (CD-ROM)
|
|
In: DTIC (2004)
|
|
BASE
|
|
Show details
|
|
9 |
Multilingual Speech and Language Processing (Le Traitement Multilingue de la Parole et du Langage) (CD-ROM)
|
|
In: DTIC (2003)
|
|
BASE
|
|
Show details
|
|
10 |
Application of Spoken and Natural Language Technologies to Lotus Notes Based Messaging and Communication
|
|
|
|
In: DTIC (2002)
|
|
BASE
|
|
Show details
|
|
11 |
Activity Detection for Information Access to Oral Communication
|
|
|
|
In: DTIC (2001)
|
|
BASE
|
|
Show details
|
|
13 |
Clustering of Context Dependent Speech Units for Multilingual Speech Recognition
|
|
|
|
In: DTIC (2000)
|
|
BASE
|
|
Show details
|
|
14 |
Multilingual Vocabularies in Automatic Speech Recognition
|
|
|
|
In: DTIC (2000)
|
|
BASE
|
|
Show details
|
|
15 |
Databases for Assessment of Military Speech Technology Equipment. (les Bases de donnees pour l'evatuation des equipements de technologie vocale militaire)
|
|
|
|
In: DTIC (2000)
|
|
BASE
|
|
Show details
|
|
16 |
The Impact of Speech Under "Stress" on Military Speech Technology. (l'Impact de la parole en condition de "stress" sur less technologies vocales militaries)
|
|
|
|
In: DTIC AND NTIS (2000)
|
|
BASE
|
|
Show details
|
|
17 |
Multilingual Text-Independent Speaker Identification
|
|
|
|
In: DTIC (2000)
|
|
BASE
|
|
Show details
|
|
19 |
Improving Acoustic Models by Watching Television
|
|
|
|
In: DTIC AND NTIS (1998)
|
|
BASE
|
|
Show details
|
|
20 |
Vocal Tract Length Normalization for Large Vocabulary Continuous Speech Recognition
|
|
|
|
In: DTIC AND NTIS (1997)
|
|
BASE
|
|
Show details
|
|
|
|