DE eng

Search in the Catalogues and Directories

Page: 1 2 3 4 5 6...42
Hits 21 – 40 of 839

21
VOCALinc
In: DTIC (2014)
BASE
Show details
22
How Autism Affects Speech Understanding in Multitalker Environments
In: DTIC (2014)
BASE
Show details
23
Development and Utility of Automatic Language Processing Technologies. Volume 2
In: DTIC (2014)
BASE
Show details
24
Biological Information Processing in Single Microtubules
In: DTIC (2014)
BASE
Show details
25
Interpreting
In: Doctoral Dissertations (2014)
BASE
Show details
26
Understanding Tonal Languages
In: DTIC (2013)
BASE
Show details
27
Cortical Signatures of Heard and Imagined Speech Envelopes
In: DTIC (2013)
BASE
Show details
28
How Autism Affects Speech Understanding in Multitalker Environments
In: DTIC (2013)
BASE
Show details
29
Computational Modeling of Emotions and Affect in Social-Cultural Interaction
In: DTIC (2013)
BASE
Show details
30
What's Wrong With Automatic Speech Recognition (ASR) and How Can We Fix It?
In: DTIC (2013)
Abstract: Seedling effort sponsored by IARPA to investigate the sources of speech recognition errors associated with noisy or unusual acoustic conditions. Research was conducted through two separate mechanisms: an in-depth study of the source of errors in the acoustic model, using a novel sampling process to quantify the effects that the two major Hidden Markov Model (HMM) assumptions have on recognition accuracy; and a broader study of problems in speech recognition relying on a surveys of area experts and relevant literature. The in-depth study demonstrates that a lack of robustness (to mismatched training/test conditions) is a significant source of error and that the sensitivity to such mismatches in the acoustic representations is a prominent source of errors. The results also show that in the case of matched conditions, one of the incorrect assumptions inherent to the standard statistical models is the dominant source of errors. A survey of automatic speech recognition (ASR) researchers and of the ASR literature provides a further sense of the community?s perspective on the topic. The report concludes with some speculations for fruitful directions of future research. The authors also suggest some extensions of this line of inquiry to other prediction and classification problems beyond speech recognition.
Keyword: *ACOUSTICS; *MARKOV PROCESSES; *SPEECH RECOGNITION; ACCURACY; ACOUSTIC EQUIPMENT; Acoustics; ADAPTERS; ASR(AUTOMATIC SPEECH RECOGNITION); AUTOMATIC; CLASSIFICATION; ERRORS; MATHEMATICAL MODELS; MODELS; PREDICTIONS; RECOGNITION; SAMPLING; SENSITIVITY; SOURCES; SPEECH; STATISTICAL ANALYSIS; SURVEYS; TRAINING; Voice Communications
URL: http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA590075
http://www.dtic.mil/docs/citations/ADA590075
BASE
Hide details
31
A Submodularity Framework for Data Subset Selection
In: DTIC (2013)
BASE
Show details
32
KEYNOTE 2 : Rebuilding the Tower of Babel - Better Communication with Standards
In: DTIC (2013)
BASE
Show details
33
Role of Autism Susceptibility Gene, CNTNAP2, in Neural Circuitry for Vocal Communication
In: DTIC (2013)
BASE
Show details
34
Raummetaphern als Brücke zwischen Internetwahrnehmung und Internetkommunikation
In: 04-4 ; sofia-Diskussionsbeiträge zur Institutionenanalyse ; 32 (2013)
BASE
Show details
35
The Representation and Processing of Tense, Aspect & Voice across Verbal Elements in English
In: DTIC (2012)
BASE
Show details
36
A Spoken Dialogue System for Command and Control
In: DTIC (2012)
BASE
Show details
37
Distributed Estimation in Sensor Networks with Imperfect Model Information: An Adaptive Learning-Based Approach
In: DTIC (2012)
BASE
Show details
38
Speech Synthesis Using Perceptually Motivated Features
In: DTIC (2012)
BASE
Show details
39
Familiar Speaker Recognition
In: DTIC (2012)
BASE
Show details
40
Machine Recognition vs Human Recognition of Voices
In: DTIC (2012)
BASE
Show details

Page: 1 2 3 4 5 6...42

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
839
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern