Headset Microphone Research Articles

Remapping Auditory-Motor Representations in Voice Production

Evidence regarding visually guided limb movements suggests that the motor system learns and maintains neural maps between motor commands and sensory feedback. Such systems are hypothesized to be used in a feed-forward control strategy that permits precision and stability without the delays of direct feedback control. Human vocalizations involve precise control over vocal and respiratory muscles. However, little is known about the sensorimotor representations underlying speech production. Here, we manipulated the heard fundamental frequency of the voice during speech to demonstrate learning of auditory-motor maps. Mandarin speakers repeatedly produced words with specific pitch patterns (tone categories). On each successive utterance, the frequency of their auditory feedback was increased by 1/100 of a semitone until they heard their feedback one full semitone above their true pitch. Subjects automatically compensated for these changes by lowering their vocal pitch. When feedback was unexpectedly returned to normal, speakers significantly increased the pitch of their productions beyond their initial baseline frequency. This adaptation was found to generalize to the production of another tone category. However, results indicate that a more robust adaptation was produced for the tone that was spoken during feedback alteration. The immediate aftereffects suggest a global remapping of the auditory-motor relationship after an extremely brief training period. However, this learning does not represent a complete transformation of the mapping; rather, it is in part target dependent.

Integrated Field and Office Tools for Bridge Management

The Wisconsin Department of Transportation's (WisDOT) Bureau of Structures Data Consolidation Project brings together all bridge-related data into a single data warehouse, the Highway Structures Information System (HSIS), which includes inventory, inspection and maintenance records, and maintenance costs. With the new HSIS, WisDOT's interactive bridge inspection forms and data procedures became incompatible. This conflict presented a timely opportunity to investigate alternative data collection tools that would be practicable in the field. This paper investigates the use of alternative field data collection technologies for bridge inspectors. The participation of bridge inspectors in identifying functional requirements led to an assembly of field tools that included the tablet PC with a shoulder carrying case, a noise-canceling headset microphone, and a tethered pen. Bridge inspectors from six districts volunteered to train on the handwriting and speech recognition technologies and then to test the tools ...

Integrated Field and Office Tools for Bridge Management

The Wisconsin Department of Transportation's (WisDOT) Bureau of Structures Data Consolidation Project brings together all bridge-related data into a single data warehouse, the Highway Structures Information System (HSIS), which includes inventory, inspection and maintenance records, and maintenance costs. With the new HSIS, WisDOT's interactive bridge inspection forms and data procedures became incompatible. This conflict presented a timely opportunity to investigate alternative data collection tools that would be practicable in the field. This paper investigates the use of alternative field data collection technologies for bridge inspectors. The participation of bridge inspectors in identifying functional requirements led to an assembly of field tools that included the tablet PC with a shoulder carrying case, a noise-canceling headset microphone, and a tethered pen. Bridge inspectors from six districts volunteered to train on the handwriting and speech recognition technologies and then to test the tools in the field. This paper presents the tool selection process, the technology choices assessed, the training of inspectors, the evaluation of the technology adoption, and the economic benefits of the new technology.

A system for spoken query information retrieval on mobile devices

With the proliferation of handheld devices, information access on mobile devices is a topic of growing relevance. This paper presents a system that allows the user to search for information on mobile devices using spoken natural-language queries. We explore several issues related to the creation of this system, which combines state-of-the-art speech-recognition and information-retrieval technologies. This is the first work that we are aware of which evaluates spoken query based information retrieval on a commonly available and well researched text database, the Chinese news corpus used in the National Institute of Standards and Technology (NIST)s TREC-5 and TREC-6 benchmarks. To compare spoken-query retrieval performance for different relevant scenarios and recognition accuracies, the benchmark queries-read verbatim by 20 speakers-were recorded simultaneously through three channels: headset microphone, PDA microphone, and cellular phone. Our results show that for mobile devices with high-quality microphones, spoken-query retrieval based on existing technologies yields retrieval precisions that come close to that for perfect text input (mean average precision 0.459 and 0.489, respectively, on TREC-6).

Portable hands-free digital voice recording and transcription device

A portable hands-free documentation system includes a headset microphone in communication with a portable recording unit having analog-to-digital and digital-to-analog conversion means therein. The portable unit further includes means for recording digital data to and reading digital data from a removable data storage medium, such as a high capacity removable computer disk. The unit also includes an output means for transmitting analog signals to a computer wherein the signals are automatically converted to text using voice recognition software.

Headset for use with a radiotelephone

A headset (10) for a radiotelephone (12) has a boom (16) that pivots about a housing (13). The headset (10) has a speaker (20) and a microphone (18). A headset detect circuit (33) determines when the headset connector (24) has been plugged into the radiotelephone's jack (26) and signals the microprocessor (60). The microprocessor (60) then connects the transmitter (68) and the receiver (70) to the headset's microphone (18) and speaker (20). To answer a call the user rotates the boom (16), either clockwise or counter clockwise, which closes a three position switch (30) and sends an off-hook signal (44) to a microprocessor (60). To end a call the user rotates the boom (16) up so it is parallel with the housing (13)

Voice-actuated, speaker-dependent control system for hospital bed

A voice-actuated environmental operator system of the kind which enables a user/patient to use simple voice commands to control a plurality of hospital environment room functions including operation of selected bed movement and room environment functions associated with a provided multi-function hospital bed. The operator system uses a conventional IBM PC, XT, AT or like computer which has been adapted for interfacing in a pass-through manner with the control unit of a provided hospital bed. The computer includes a voice card and associated voice recognition and training software for interpreting and translating voice input into digital information readable by a controller card for operating a plurality of bed motor and room function commands. The controller card includes a plurality of relay switch devices, each of which are dedicated to performing a specific bed movement or room function. An FCC registered data access arrangement is also provided to the controller card for telephone interface capability. In a first embodiment, data communication between the computer and the provided hospital bed's control unit is by pass-through hard wire cable interface connection between bed control unit and the DB9 and DB15 serial port connectors on the back of the computer. The DB9 and DB15 serial port connectors are desoddered off the computer's motherboard and wired directly to the controller board. A headset microphone assembly wearable by a patient user is provided to the system for transmitting voice input to said voice recognition means and receiving system command confirmation signals and telephone communications.

RADCOM: a computerized translation device for use during fluoroscopic examination of non-English-speaking patients.

We developed and have implemented RADCOM (RADiology COMmunicator), a computerized speech-based language translator for use during fluoroscopic examination of non-English-speaking patients. It is controlled completely by voice commands issued into a headset microphone. The system output is digital audio via a small speaker, in the native language of the patient. RADCOM currently supports more than 40 commands in more than a dozen languages. The language data base is easily expandable. We have performed more than 20 fluoroscopic examinations with the RADCOM system. The non-English-speaking patients respond well, following the selected instructions appropriately.

An acoustic-phonetic data base

DARPA has sponsored the design and collection of a large speech data base. Six hundred and thirty speakers read ten sentences each. Two sentences were constant for all speakers; the remaining eight sentences were selected from a set of 450 designed at MIT and 1890 selected at TI from text sources. The set of sentences is phonetically rich, balanced, and deep. Although all recordings were made in Dallas, we sampled as many varieties of American English as possible. Selection of volunteer speakers was based on their childhood locality to give a balanced representation of geographical origins. The subject population is adult; 70% male; young (63% in their twenties); well educated (78% with bachelor's degree); and predominantly white (96%). Recordings were made in a noise-reducing sound booth using a Sennheiser headset microphone and digitized at 20 kHz. A natural reading style was encouraged. The recordings are complete, and time-registered phonetic transcriptions are being added to the 6300 speech files at MIT. A version of the complete data base (16-kHz sample rate, with acoustic-phonetic transcriptions—approximately 50 megabytes of data) will be made available to researchers through the National Bureau of Standards. [Work supported by DARPA.]

Post-auricle contoured headset for two-way voice communication

A miniaturized headset of the post-auricle type is disclosed. The headset microphone may be located in the capsule, or at the end of a swivelable boom near the wearer's mouth. In either case, the headset capsule is contoured to fit over the mastoid process of the skull, in order to provide better weight distribution, comfort and stability. The headset capsule is further contoured by providing a front-to-back concavity in the upper portions of the capsule's sides, so as to generally conform to the curvature of the wearer's head.

Issues and answers in evaluation of automatic speech recognizers

An extensive comparison of commercially available automatic speech recognition systems revealed a wide range of performance characteristics. On an isolated word, speaker dependent database, the percentage of errors (i.e., 100% − correct recognition%) ranged over two orders of magnitude for the 10 210 utterances tested. The vocabulary consisted of 11 words (the 10 digits plus “oh”) collected from five males and five females in a moderate office-noise environment. Simultaneous recordings were made with headset and table microphones. Every attempt was made to assure that the systems tested were operating optimally, often with vendor cooperation. Although all systems performed better with data recorded from the headset microphone than with the table microphone, the amount of degradation was not uniform across systems. Special problems and solutions for performing these tests will be discussed.

Headset Microphone for Communication in Noise Fields of 135 db and Higher

A headset microphone is described which will give a calculated 84% word articulation in a noise field of 140 db, such as may be found during trimming operations on jet engines and at missile test stands and launching sites. The M-87/AIC microphone and H-143/AIC earphone described at the May, 1958 meeting are employed with a noise shield and a specially designed ear cushion is a hard shell, circumaural type with a grease-filled sealing pad. The internal volume is divided by a flexible plastic sheath which lays loosely against the auricle and couples the earphone to the ear with a cavity of approximately 10 cc. The sheath is perforated with a few small holes which couple the larger volume of the shell to the ear in order to obtain increased attenuation below 500 cps. The acoustic isolation of the sheath above 500 cps also minimizes the effect of standing waves in the larger cavity upon the response and attenuation characteristic of the headset. The articulation performance cited above is estimated assuming 200-mw power available with 10-db peak clipping. This can be obtained from the AN/AIC-17 interphone system used by Air Force ground crews. Indicative articulation scores for jet noise fields up to 160 db, and tolerable exposure times based upon WADC damage risk criteria, are reported. [The work was supported by Contract AF 33(600)-33172 from WADC Communication and Navigation Laboratories under the direction of T. P. Mountz.]