1 |
Compressed Domain Automatic Level Control Based on ITU-T G.722.2
|
|
|
|
In: DTIC (2012)
|
|
BASE
|
|
Show details
|
|
2 |
Comment ameliorer la selection et le traitement des messages verbaux? (How to Improve the Selection and Processing of Verbal Messages)
|
|
|
|
In: DTIC (2005)
|
|
BASE
|
|
Show details
|
|
3 |
Speech Intelligibility with a Bone Vibrator
|
|
|
|
In: DTIC (2005)
|
|
Abstract:
The FELIN project (Foot soldier with Integrated Equipment and Connectivity) of the French Military Procurement Agency aims at gearing tomorrow's foot soldier with "flexible and maneuvering" equipment. Among its requirements is that foot soldiers are fitted with a communications headband operating through bone conduction. The main advantage of listening through bone conduction is that it allows for the transmission of information to the soldier, while leaving the soldier's ears free to perceive the surrounding environment. This device is light, not bulky, and is quite comfortable. This laboratory assessment compared the voice intelligibility scores of a prototype bone conduction device with those obtained by Peltor's (trademark) militarized COMTAC-type headset. The COMTAC headset is a hearing device (i.e., fitted with two microphones, left and right, to reproduce a spatial hearing capability). Both technologies allow for orientation in space using acoustic cues. Tests were performed in silence and in operationally realistic noise conditions (reproducing the noisy environment inside an armored vehicle). Voice material consisted of nonsense CVC words (Consonant-Vowel-Consonant) spoken by two speakers of different genders. In silence, the prototype bone vibrator headband and the COMTAC headset obtained the same intelligibility score. In noise, the performance of the prototype headband was slightly lower than that of the COMTAC headset. One of the reasons for this is that in a noisy environment, finding the right position for the vibrator to obtain optimal hearing is difficult, and the voice transmission level is too low. In brief, bone conduction technology (reduced here to the mere listening function) has an appreciable initial potential, based on the performance obtained in silence. However, design improvements will be needed to reach the voice levels required for intelligibility in loud environments (notably for use in armored vehicles). ; See also ADM001856. Presented at the RTO Human Factors and Medicine (HFM) Symposium, New Directions for Improving Audio Effectiveness (Nouvelles orientations pour l'amelioration des techniques audio) held in Amersfoort, The Netherlands, on 11-13 Apr 2005. Pub. in the Proceedings of New Directions for Improving Audio Effectiveness (Nouvelles orientations pour l'amelioration des techniques audio, RTO-MP-HFM-123), p8-1 to 8-20, Paper 8, Apr 2005. The original document contains color images.
|
|
Keyword:
*ARMORED VEHICLES; *BONE CONDUCTION HEADBAND; *BONES; *INTELLIGIBILITY; *SKULL; *SOUND TRANSMISSION; *VIBRATION; *VOICE COMMUNICATIONS; Acoustics; COCHLEA; COMPONENT REPORTS; COMTAC HEADSET; CONDUCTIVITY; CVC(CONSONANT VOWEL CONSONANT); FOREIGN REPORTS; FRANCE; HEADGEAR; INFANTRY PERSONNEL; INTELLIGIBILITY MEASUREMENT; LABORATORY TESTS; LISTENING TESTS; LOW INTENSITY; LOW INTENSITY SOUND; MICROPHONES; Military Forces and Organizations; NATO FURNISHED; NOISE(SOUND); REVERBERATION CHAMBERS; SIGNAL TO NOISE RATIO; SILENCE; SPEECH TRANSMISSION; SYMPOSIA; Voice Communications
|
|
URL: http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA455883 http://www.dtic.mil/docs/citations/ADA455883
|
|
BASE
|
|
Hide details
|
|
4 |
Towards Multilingual Interoperability in Automatic Speech Recognition
|
|
|
|
In: DTIC (2000)
|
|
BASE
|
|
Show details
|
|
5 |
Clustering of Context Dependent Speech Units for Multilingual Speech Recognition
|
|
|
|
In: DTIC (2000)
|
|
BASE
|
|
Show details
|
|
6 |
Speech Intelligibility of Native and Non-Native Speech
|
|
|
|
In: DTIC (2000)
|
|
BASE
|
|
Show details
|
|
7 |
Auditory Features Underlying Cross-Language Human Capabilities in Stop Consonant Discrimination
|
|
|
|
In: DTIC (2000)
|
|
BASE
|
|
Show details
|
|
8 |
Vowel System Modeling: A Complement to Phonetic Modeling in Language Identification
|
|
|
|
In: DTIC (2000)
|
|
BASE
|
|
Show details
|
|
9 |
Comparing Three Methods to Create Multilingual Phone Models for Vocabulary Independent Speech Recognition Tasks
|
|
|
|
In: DTIC (2000)
|
|
BASE
|
|
Show details
|
|
10 |
Speech Recognition of Non-Native Speech Using Native and Non-Native Acoustic Models
|
|
|
|
In: DTIC (2000)
|
|
BASE
|
|
Show details
|
|
11 |
Acoustic-Phonetic Modeling of Non-Native Speech for Language Identification
|
|
|
|
In: DTIC (2000)
|
|
BASE
|
|
Show details
|
|
12 |
Multilingual Vocabularies in Automatic Speech Recognition
|
|
|
|
In: DTIC (2000)
|
|
BASE
|
|
Show details
|
|
13 |
Speech Recognition by Goats, Wolves, Sheep and Non-Natives
|
|
|
|
In: DTIC (2000)
|
|
BASE
|
|
Show details
|
|
14 |
A Military Operational Automatic Interpreting System
|
|
|
|
In: DTIC (2000)
|
|
BASE
|
|
Show details
|
|
16 |
Multilingual Text-Independent Speaker Identification
|
|
|
|
In: DTIC (2000)
|
|
BASE
|
|
Show details
|
|
18 |
Language Adaptive LVCSR Through Polyphone Decision Tree Specialization
|
|
|
|
In: DTIC (2000)
|
|
BASE
|
|
Show details
|
|
19 |
How Foreign are 'Foreign' Speech Sounds? Implications for Speech Recognition and Speech Synthesis
|
|
In: DTIC (2000)
|
|
BASE
|
|
Show details
|
|
20 |
Speech and Language Technology: A UK Strategy (SALTUS-2000)
|
|
|
|
In: DTIC AND NTIS (1988)
|
|
BASE
|
|
Show details
|
|
|
|