1 |
Postcolonial literature and world Englishes : a corpus-based approach of modes of representation of the non-standard in writing [Online resource]
|
|
|
|
In: International journal of literary linguistics : IJLL 6 (2017) 1, Art. 3, 1-24
|
|
Linguistik-Repository
|
|
Show details
|
|
4 |
Technology for Maintenance Procedure Validation
|
|
|
|
In: DTIC AND NTIS (2001)
|
|
BASE
|
|
Show details
|
|
5 |
Segment-Based Acoustic Models for Continuous Speech Recognition.
|
|
|
|
In: DTIC AND NTIS (1994)
|
|
BASE
|
|
Show details
|
|
6 |
Segment-Based Acoustic Models for Continuous Speech Recognition.
|
|
|
|
In: DTIC AND NTIS (1994)
|
|
BASE
|
|
Show details
|
|
7 |
Word and Subword Modelling in a Segment-Based HMM Word Spotter Using a Data Analytic Approach
|
|
|
|
In: DTIC AND NTIS (1992)
|
|
BASE
|
|
Show details
|
|
8 |
Speech Recognition: Acoustic-Phonetic Knowledge Acquisition and Representation
|
|
|
|
In: DTIC AND NTIS (1988)
|
|
Abstract:
The long-term research goal is to develop and implement speaker- independent continuous speech recognition systems. It is believed that the proper utilization of speech-specific knowledge is essential for such advanced systems. This research is thus directed toward the acquisition, quantification, and representation, of acoustic-phonetic and lexical knowledge, and the application of this knowledge to speech recognition algorithms. In addition, we are exploring new speech recognition alternatives based on artificial intelligence and connectionist techniques. We developed a statistical model for predicting the acoustic realization of stop consonants in various positions in the syllable template. A unification-based grammatical formalism was developed for incorporating this model into the lexical access algorithm. We provided an information-theoretic justification for the hierarchical structure of the syllable template. We analyzed segmented duration for vowels and fricatives in continuous speech. Based on contextual information, we developed durational models for vowels and fricatives that account for over 70% of the variance, using data from multiple, unknown speakers. We rigorously evaluated the ability of human spectrogram readers to identify stop consonants spoken by many talkers and in a variety of phonetic contexts. Incorporating the declarative knowledge used by the readers, we developed a knowledge-based system for stop identification. We achieved comparable system performance to that of the readers. We developed a technique for phonetic classification using artificial neural nets (ANN). Vowel classification accuracy was achieved, ranging from 66 to 100% under varying experimental conditions.
|
|
Keyword:
*ACOUSTIC DATA; *ACOUSTIC RECORDING SYSTEMS; *ALGORITHMS; *SPEECH RECOGNITION; ACCESS; ACCURACY; ARTIFICIAL INTELLIGENCE; CLASSIFICATION; DATA ACQUISITION; HIERARCHIES; HUMANS; KNOWLEDGE ACQUISITION; KNOWLEDGE REPRESENTATION; LANGUAGE; LEXICOGRAPHY; LONG RANGE(TIME); MATHEMATICAL MODELS; NEURAL NETS; PHONETICS; SEGMENTED; SPEECH; STATISTICAL ANALYSIS; SYLLABLES; TEMPLATES; TIME; Voice Communications; VOWELS; WUNR049542
|
|
URL: http://www.dtic.mil/docs/citations/ADA203081 http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA203081
|
|
BASE
|
|
Hide details
|
|
9 |
Word Hypothesization for Large-Vocabulary Speech Understanding Systems.
|
|
|
|
In: DTIC AND NTIS (1977)
|
|
BASE
|
|
Show details
|
|
|
|