2 |
Respirator Speech Intelligibility Testing with an Experienced Speaker
|
|
|
|
In: DTIC (2015)
|
|
BASE
|
|
Show details
|
|
3 |
How Autism Affects Speech Understanding in Multitalker Environments
|
|
|
|
In: DTIC (2014)
|
|
BASE
|
|
Show details
|
|
4 |
How Autism Affects Speech Understanding in Multitalker Environments
|
|
|
|
In: DTIC (2013)
|
|
BASE
|
|
Show details
|
|
5 |
Effects of Speech Intensity on the Callsign Acquisition Test (CAT) and Modified Rhyme Test (MRT) Presented in Noise
|
|
|
|
In: DTIC (2012)
|
|
BASE
|
|
Show details
|
|
6 |
Performance Assessments of Two-Way, Free-Form, Speech-to-Speech Translation Systems for Tactical Use
|
|
|
|
In: DTIC (2011)
|
|
BASE
|
|
Show details
|
|
7 |
USSS-MITLL 2010 Human Assisted Speaker Recognition
|
|
|
|
In: DTIC (2010)
|
|
BASE
|
|
Show details
|
|
9 |
Automated Speech Intelligibility System for Head-Borne Personal Protective Equipment: Proof of Concept
|
|
|
|
In: DTIC (2008)
|
|
BASE
|
|
Show details
|
|
10 |
Linking Semantic and Knowledge Representations in a Multi-Domain Dialogue System
|
|
|
|
In: DTIC (2007)
|
|
BASE
|
|
Show details
|
|
11 |
Comparing Evaluation Metrics for Sentence Boundary Detection
|
|
|
|
In: DTIC (2007)
|
|
Abstract:
In recent NIST evaluations on sentence boundary detection, a single error metric was used to describe performance. Additional metrics, however, are available for such tasks, in which a word stream is partitioned into subunits. This paper compares alternative evaluation metrics including the NIST error rate, classification error rate per word boundary, precision and recall, ROC curves, DET curves, precision-recall curves, and area under the curves and discusses advantages and disadvantages of each. Unlike many studies in machine learning, we use real data for a real task. We find benefit from using curves in addition to a single metric. Furthermore, we find that data skew has an impact on metrics, and that differences among different system outputs are more visible in precision-recall curves. Results are expected to help us better understand evaluation metrics that should be generalizable to similar language processing tasks. ; Presented at the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (32nd) held in Honolulu, Hawaii on 15-20 April 2007. Published in the Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (32nd), 2007. The original document contains color images.
|
|
Keyword:
*COMPUTATIONAL LINGUISTICS; *EVALUATION METRICS; *LANGUAGE PROCESSING; *SENTENCE BOUNDARY DETECTION; *SPEECH RECOGNITION; *TEST AND EVALUATION; Equipment and Methods; ERRORS; LEARNING MACHINES; Linguistics; MACHINE LEARNING; NATURAL LANGUAGE; PRECISION; RECALL; ROC CURVES; ROC(RECEIVER OPERATING CHARACTERISTIC); SYMPOSIA; Test Facilities; Voice Communications
|
|
URL: http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA463058 http://www.dtic.mil/docs/citations/ADA463058
|
|
BASE
|
|
Hide details
|
|
12 |
Testing Template and Testing Concept of Operations for Speaker Authentication Technology
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
13 |
Speech Intelligibility with Acoustic and Contact Microphones
|
|
|
|
In: DTIC (2005)
|
|
BASE
|
|
Show details
|
|
14 |
Conversational Telephone Speech Corpus Collection for the NIST Speaker Recognition Evaluation 2004
|
|
|
|
In: DTIC (2004)
|
|
BASE
|
|
Show details
|
|
15 |
The Pragmatics of Taking a Spoken Language System Out of the Laboratory
|
|
|
|
In: DTIC (2003)
|
|
BASE
|
|
Show details
|
|
16 |
A Three-Tiered Evaluation Approach for Interactive Spoken Dialogue Systems
|
|
|
|
In: DTIC (2001)
|
|
BASE
|
|
Show details
|
|
17 |
Preserving Spectral Contrast in Amplitude Compression for Hearing Aids
|
|
|
|
In: DTIC AND NTIS (2001)
|
|
BASE
|
|
Show details
|
|
18 |
Speech Intelligibility of Native and Non-Native Speech
|
|
|
|
In: DTIC (2000)
|
|
BASE
|
|
Show details
|
|
19 |
Acoustic-Phonetic Modeling of Non-Native Speech for Language Identification
|
|
|
|
In: DTIC (2000)
|
|
BASE
|
|
Show details
|
|
20 |
Smoothing Disjoint Formant Track Boundaries Caused by Waveform Substitution in Packet Voice Communication.
|
|
|
|
In: DTIC AND NTIS (1996)
|
|
BASE
|
|
Show details
|
|
|
|