Publications
The Marine Stratus Initiative at San Francisco International Airport
June 25, 1996
Project Report
Published in:
MIT Lincoln Laboratory Report ATC-252
Summary
San Francisco International Airport is one of the busiest airports in the United States and one of the highest delay airports in terms of total aircraft delay hours and number of imposed air traffic delay programs. As with most airports, weather is the primary cause of aircraft delay. In particular, the local airspace is prone to regular occurrences of low cloud ceiling conditions due to intrusion of marine air from the eastern Pacific Ocean from May through September. Typically, this layer of stratus clouds forms in the San Francisco Bay area overnight and dissipates during the middle to late morning. The timing of the stratus cloud dissipation is such that it frequently poses a threat to the morning arrival push of air traffic into San Francisco. Weather forecasters at the Central Weather Service Unit (CWSU) at the Oakland AirRoute Traffic Control Center are responsible for providing a forecast whether or not the cloudiness will impact morning traffic operations. This information is used for decision making by the Traffic Management Unit at Oakland Center in order to optimally match arriving traffic demand to available airport capacity. As part of the FAA's Integrated Terminal Weather System, the Weather Sensing Group at MIT Lincoln Laboratory has begun an effort entitled the "Marine Stratus Initiative." Its objective is to provide improved weather information and forecast guidance to the Oakland CWSU, which is responsible for providing weather forecasts to air traffic managers. During 1995, the main focus of the project was the design and implementation of a data acquisition, communication, and display infrastructure that provides forecasters with new sources of weather data and information. These initial capabilities were tested during an operational demonstration in August and September. As the project continues, the intent is to improve these new data sources and develop an automated or semi-automated algorithm that will process raw information to provide weather forecasters with numerical guidance to assist them in the forecast process. A description of airport operations at San Francisco and the impact of marine stratus are presented. An explanation is given of the marine stratus phenomenology and the primary factors contributing to cloud dissipation. This conceptual model of the dissipation process is used to define system requirements. A description of the hardware, communications, and display subsystems is provided. An overview of the 1995 demonstration, including user comments, is presented, as well as future plans for meeting the longer-term objectives of the project.
Summary
San Francisco International Airport is one of the busiest airports in the United States and one of the highest delay airports in terms of total aircraft delay hours and number of imposed air traffic delay programs. As with most airports, weather is the primary cause of aircraft delay. In particular...
READ MORE
Air Force planetary defense system: initial field test results
June 1, 1996
Conference Paper
Published in:
Proc. of the Fifth Int. Conf. on Space '96: Engineering, Construction, and Operations in Space V, 1-6 June 1996, pp. 46-53.
Topic:
R&D area:
R&D group:
Summary
Over the past several years, the Air Force has been developing new devices and technology for the detection and tracking of earth orbiting satellites. This technology has been targeted to provide an upgraded capability for an operational space surveillance system called GEODSS. Currently, a number of GEODSS systems are deployed around the world as part of the world-wide space surveillance system operated by the US Air Force. Each GEODSS site is currently equipped with 1-meter class telescopes and EBSICON detector systems which represent 1970's technology. The Air Force is now in the process of upgrading the GEODSS system to achieve the performance offered by state of the art detector systems. Under Air Force sponsorship, Lincoln Laboratory has developed a new generation of sensitive, large format, frame transfer CCD focal planes for GEODSS. These focal planes have been installed in a new generation of cameras and are currently undergoing testing at the Lincoln Laboratory Experimental Test Site (ETS). When equipped with the new focal plane and camera technology, the modest sized GEODSS telescopes have considerable capability to conduct large coverage, sensitive searches for earth crossing asteroids. Theoretical analysis has indicated that the CCD equipped GEODSS telescope will be capable of achieving a limiting magnitude of 22, over a 2 sq/deg field of view, with about 100 seconds of integration. This is comparable to the sensitivity of considerably larger telescopes equipped with current cameras. In addition to the high sensitivity, the CCD is configured for frame transfer operations which are well suited to asteroid search operations. This paper will present the results of the initial system tests conducted at the ETS and will discuss how this technology fits into a concept of operations for a planetary defense system based on the Air Force developed technology.
Summary
Over the past several years, the Air Force has been developing new devices and technology for the detection and tracking of earth orbiting satellites. This technology has been targeted to provide an upgraded capability for an operational space surveillance system called GEODSS. Currently, a number of GEODSS systems are deployed...
READ MORE
Six-sector antenna for the GPS-squitter en-route ground station
May 31, 1996
Project Report
Published in:
MIT Lincoln Laboratory Report ATC-248
Summary
Summary: A six-sector antenna for a pole-mounted GPS-Squitter en-route ground station was designed, built, and tested. The fan beam of each of the six sectors of the antenna covers a 60- degree azimuthal sector. Together, the six uniformly-spaced, contiguous 60-degree sectors cover the complete 360 degrees of azimuth at the two Mode S frequencies, 1030 and 1090 MHz. When equipped with its receivers, the antenna achieves a maximum operational squitter reception range in excess of 200nmi. Physically, the antenna consists of six vertical 12-element linear arrays spaced uniformly round the circumference of an imaginary vertical circular cylinder and lying parallel to its axis. Six reflectors in the form of parabolic cylinders are mounted behind the linear arrays, one per array, to define the six separate sector beams. The complete radome-enclosed assembly is a cylinder eight feet tall and 23 inches in diameter. It weighs 250 pounds.
Summary
Summary: A six-sector antenna for a pole-mounted GPS-Squitter en-route ground station was designed, built, and tested. The fan beam of each of the six sectors of the antenna covers a 60- degree azimuthal sector. Together, the six uniformly-spaced, contiguous 60-degree sectors cover the complete 360 degrees of azimuth at the...
READ MORE
Improving wordspotting performance with artificially generated data
May 9, 1996
Conference Paper
Published in:
Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, ICASSP, 9 May 1996, pp. 526-9.
Topic:
R&D area:
Summary
Lack of training data is a major problem that limits the performance of speech recognizers. Performance can often only be improved by expensive collection of data from many different talkers. This paper demonstrates that artificially transformed speech can increase the variability of training data and increase the performance of a wordspotter without additional expensive data collection. This approach was shown to be effective on a high-performance whole-word wordspotter on the Switchboard Credit Card database. The proposed approach used in combination with a discriminative training approach increased the Figure of Merit of the wordspotting system by 9.4% percentage points (62.5% to 71.9%). The increase in performance provided by artificially transforming speech was roughly equivalent to the increase that would have been provided by doubling the amount of training data. The performance of the wordspotter was also compared to that of human listeners who were able to achieve lower error rates because of improved consonant recognition.
Summary
Lack of training data is a major problem that limits the performance of speech recognizers. Performance can often only be improved by expensive collection of data from many different talkers. This paper demonstrates that artificially transformed speech can increase the variability of training data and increase the performance of a...
READ MORE
Automatic dialect identification of extemporaneous, conversational, Latin American Spanish Speech
May 7, 1996
Conference Paper
Published in:
Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Vol. 2, ICASSP, 7-10 May 1996, pp. 777-780.
Topic:
R&D area:
Summary
A dialect identification technique is described that takes as input extemporaneous, conversational speech spoken in Latin American Spanish and produces as output a hypothesis of the dialect. The system has been trained to recognize Cuban and Peruvian dialects of Spanish, but could be extended easily to other dialects (and languages) as well. Building on our experience in automatic language identification, the dialect-ID system uses an English phone recognizer trained on the TIMIT corpus to tokenize training speech spoken in each Spanish dialect. Phonotactic language models generated from this tokenized training speech are used during testing to compute dialect likelihoods for each unknown message. This system has an error rate of 16% on the Cuban/Peruvian two-alternative forced-choice test. We introduce the new "Miami" Latin American Spanish speech corpus that is capable of supporting our research into the future.
Summary
A dialect identification technique is described that takes as input extemporaneous, conversational speech spoken in Latin American Spanish and produces as output a hypothesis of the dialect. The system has been trained to recognize Cuban and Peruvian dialects of Spanish, but could be extended easily to other dialects (and languages)...
READ MORE
Fine structure features for speaker identification
May 7, 1996
Conference Paper
Published in:
Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, ICASSP, Vol. 2, Speech (Part II), 7-10 May 1996, pp. 689-692.
Topic:
R&D area:
Summary
The performance of speaker identification (SID) systems can be improved by the addition of the rapidly varying "fine structure" features of formant amplitude and/or frequency modulation and multiple excitation pulses. This paper shows how the estimation of such fine structure features can be improved further by obtaining better estimates of formant frequency locations and uncovering various sources of error in the feature extraction systems. Most female telephone speech showed "spurious" formants, due to distortion in the telephone network. Nevertheless, SID performance was greatest with these spurious formants as formant estimates. A new feature has also been identified which can increase SID performance: cepstral coefficients from noise in the estimated excitation waveform. Finally, statistical tools have been developed to explore the relative importance of features used for SID, with the ultimate goal of uncovering the source of the features that provide SID performance improvement.
Summary
The performance of speaker identification (SID) systems can be improved by the addition of the rapidly varying "fine structure" features of formant amplitude and/or frequency modulation and multiple excitation pulses. This paper shows how the estimation of such fine structure features can be improved further by obtaining better estimates of...
READ MORE
Low rate coding of the spectral envelope using channel gains
May 7, 1996
Conference Paper
Published in:
Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, ICASSP, Vol. 2, 7-10 May 1996, pp. 769-772.
Topic:
R&D area:
Summary
A dual rate embedded sinusoidal transform coder is described in which a core 14th order allpole coder operating at 2400 b/s is augmented with a set of channel gain residuals in order to operate at the higher 4800 b/s rate. The channel gains are a set of non-uniformly spaced samples of the spline envelope and constitute a lowpass estimate of the short-time vocal tract magnitude spectrum. The channel gain residuals represent the difference between the spline envelope and the quantized 14th order allpole spectrum at the channel gain frequencies. The channel gain residuals are coded using pitch dependent scalar quantization. Informal listening indicates that the quality of the embedded coder at 4800 b/s is comparable to that of an existing high quality 4800 b/s allpole coder.
Summary
A dual rate embedded sinusoidal transform coder is described in which a core 14th order allpole coder operating at 2400 b/s is augmented with a set of channel gain residuals in order to operate at the higher 4800 b/s rate. The channel gains are a set of non-uniformly spaced samples...
READ MORE
The effects of handset variability on speaker recognition performance: experiments on the switchboard corpus
May 7, 1996
Conference Paper
Published in:
Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, ICASSP, Vol. 1, 7-10 May 1996, pp. 113-116.
Topic:
R&D area:
Summary
This paper presents an empirical study of the effects of handset variability on text-independent speaker recognition performance using the Switchboard corpus. Handset variability occurs when training speech is collected using one type of handset, but a different handset is used for collecting test speech. For the Switchboard corpus, the calling telephone number associated with a file is used to imply the handset used. Analysis of experiments designed to focus on handset variability on the SPIDRE database and the May95 NIST speaker recognition evaluation database, show that a performance gap between matched and mismatched handset tests persists even after applying several standard channel compensation techniques. Error rates for the mismatched tests are over 4 times those for the matched tests. Lastly, a new energy dependent cepstral mean subtraction technique is proposed to compensate for nonlinear distortions, but is not found to improve performance on the databases used.
Summary
This paper presents an empirical study of the effects of handset variability on text-independent speaker recognition performance using the Switchboard corpus. Handset variability occurs when training speech is collected using one type of handset, but a different handset is used for collecting test speech. For the Switchboard corpus, the calling...
READ MORE
Unsupervised topic clustering of switchboard speech messages
May 7, 1996
Conference Paper
Published in:
Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, ICASSP, Vol. 1, 7-10 May 1996, pp. 315-318.
Topic:
R&D area:
Summary
This paper presents a statistical technique which can be used to automatically group speech data records based on the similarity of their content. A tree-based clustering algorithm is used to generate a hierarchical structure for the corpus. This structure can then be used to guide the search for similar material in data from other corpora. The SWITCHBOARD Speech Corpus was used to demonstrate these techniques, since it provides sets of speech files which are nominally on the same topic. Excellent automatic clustering was achieved on the truth text transcripts provided with the SWITCHBOARD corpus, with an average cluster purity of 97.3%. Degraded clustering was achieved using the output transcriptions of a speech recognizer, with a clustering purity of 61.4%.
Summary
This paper presents a statistical technique which can be used to automatically group speech data records based on the similarity of their content. A tree-based clustering algorithm is used to generate a hierarchical structure for the corpus. This structure can then be used to guide the search for similar material...
READ MORE
ASR-9 Weather System Processor (WSP): wind shear algorithms performance assessment
May 7, 1996
Project Report
Published in:
MIT Lincoln Laboratory Report ATC-247
Summary
Lincoln Laboratory has developed a prototype Airport Surveillance Radar Weather Systems Processor (ASR-WSP) that has been used for field measurements and operational demonstrations since 1987. Measurements acquired with this prototype provide an extensive data base for development and validation of the algorithms the WSP uses to generate operational wind shear information for Air Traffic Controllers. This report addresses the performance of the current versions of the WSP's microburst and gust front wind shear detection algorithms on available data from each of the WSP's operational sites. Evaluation of the associated environmental characteristics (e.g., storm structure, radar ground clutter environment) allows for generalization of results of the other major U.S. climatic regimes where the production version of WSP will be deployed.
Summary
Lincoln Laboratory has developed a prototype Airport Surveillance Radar Weather Systems Processor (ASR-WSP) that has been used for field measurements and operational demonstrations since 1987. Measurements acquired with this prototype provide an extensive data base for development and validation of the algorithms the WSP uses to generate operational wind shear...
READ MORE