SEARCH · Engineering Papers
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Technology and systems for effective verbal communication with computers were developed. A continuous speech recognition system for verbal input, a word spotting system to locate key words in conversational speech, prosodic tools to aid speech analysis, and a prerecorded voice response system for speech output are described.
Many current and future NASA missions make extreme demands on mission personnel both in terms of work load and in performing under difficult environmental conditions. In situations where hands are impeded or needed for other tasks, eyes are busy attending to the environment, or tasks are sufficiently complex that ease of use of the interface becomes critical, spoken natural language dialog systems offer unique input and output modalities that can improve efficiency and safety. They also offer new capabilities that would not otherwise be available. For example, many NASA applications require astronauts to use computers in micro-gravity or while wearing space suits. Under these circumstances, command and control systems that allow users to issue commands or enter data in hands-and eyes-busy situations become critical. Speech recognition technology designed for current commercial applications limits the performance of the open-ended state-of-the-art dialog systems being developed at NASA. For example, today's recognition systems typically listen to user input only during short segments of the dialog, and user input outside of these short time windows is lost. Mistakes detecting the start and end times of user utterances can lead to mistakes in the recognition output, and the dialog system as a whole has no way to recover from this, or any other, recognition error. Systems also often require the user to signal when that user is going to speak, which is impractical in a hands-free environment, or only allow a system-initiated dialog requiring the user to speak immediately following a system prompt. In this project, SRI has developed software to enable speech recognition in a hands-free, open-microphone environment, eliminating the need for a push-to-talk button or other signaling mechanism. The software continuously captures a user's speech and makes it available to one or more recognizers. By constantly monitoring and storing the audio stream, it provides the spoken dialog manager extra flexibility to recognize the signal with no audio gaps between recognition requests, as well as to rerecognize portions of the signal, or to rerecognize speech with different grammars, acoustic models, recognizers, start times, and so on. SRI expects that this new open-mic functionality will enable NASA to develop better error-correction mechanisms for spoken dialog systems, and may also enable new interaction strategies.
A new method for analyzing nonlinear and nonstationary data has been developed, and the natural applications are to speech and sound signals. The key part of the method is the Empirical Mode Decomposition method with which any complicated data set can be decomposed into a finite and often small number of Intrinsic Mode Functions (IMF). An IMF is defined as any function having the same numbers of zero-crossing and extrema, and also having symmetric envelopes defined by the local maxima and minima respectively. The IMF also admits well-behaved Hilbert transform. This decomposition method is adaptive, and, therefore, highly efficient. Since the decomposition is based on the local characteristic time scale of the data, it is applicable to nonlinear and nonstationary processes. With the Hilbert transform, the Intrinsic Mode Functions yield instantaneous frequencies as functions of time, which give sharp identifications of imbedded structures. This method invention can be used to process all acoustic signals. Specifically, it can process the speech signals for Speech synthesis, Speaker identification and verification, Speech recognition, and Sound signal enhancement and filtering. Additionally, as the acoustical signals from machinery are essentially the way the machines are talking to us. Therefore, the acoustical signals, from the machines, either from sound through air or vibration on the machines, can tell us the operating conditions of the machines. Thus, we can use the acoustic signal to diagnosis the problems of machines.
We are developing a system for synthesizing image sequences the simulate the facial motion of a speaker. To perform this synthesis, we are pursuing two major areas of effort. We are developing the necessary computer graphics technology to synthesize a realistic image sequence of a person speaking selected speech sequences. Next, we are developing a model that expresses the relation between spoken phonemes and face/mouth shape. A subject is video taped speaking an arbitrary text that contains expression of the full list of desired database phonemes. The subject is video taped from the front speaking normally, recording both audio and video detail simultaneously. Using the audio track, we identify the specific video frames on the tape relating to each spoken phoneme. From this range we digitize the video frame which represents the extreme of mouth motion/shape. Thus, we construct a database of images of face/mouth shape related to spoken phonemes. A selected audio speech sequence is recorded which is the basis for synthesizing a matching video sequence; the speaker need not be the same as used for constructing the database. The audio sequence is analyzed to determine the spoken phoneme sequence and the relative timing of the enunciation of those phonemes. Synthesizing an image sequence corresponding to the spoken phoneme sequence is accomplished using a graphics technique known as morphing. Image sequence keyframes necessary for this processing are based on the spoken phoneme sequence and timing. We have been successful in synthesizing the facial motion of a native English speaker for a small set of arbitrary speech segments. Our future work will focus on advancement of the face shape/phoneme model and independent control of facial features.
In recent years, the application of automatic speech recognition has gained popularity across diverse industries, including aviation. Given the many applications focusing on transcribing air traffic control and management communication, this paper explores the training of OpenAI's Whisper model across multiple existing public and private air traffic control voice datasets in an effort to improve robustness. Combining roughly 60+ hours of various air traffic datasets, our goal is to train a unified Whisper model and expect an average word error rate reduction across testing datasets. Furthermore, this work aims to understand the data quantity requirements for achieving state-of-the art results by comprehensively training Whisper on varying dataset sizes. This work has the potential to improve automatic speech recognition performance across the domain, improve understanding of the quantity of data required by an aviation speech recognition system, and lastly provide metrics to compare and improve upon in future research.
Techniques developed by NASA for spaceflight instrumentation were used in the design of a quantizer for speech-decoding. Computer simulation of the actions of the quantizer was tested with synthesized and real speech signals. Results were evaluated by a phometician. Topics discussed include the relationship between the number of quantizer levels and the required sampling rate; reconstruction of signals; digital filtering; speech recording, sampling, and storage, and processing results.
A speech signal is analyzed by applying the signal to formant filters which derive first, second and third signals respectively representing the frequency of the speech waveform in the first, second and third formants. A first pulse train having approximately a pulse rate representing the average frequency of the first formant is derived; second and third pulse trains having pulse rates respectively representing zero crossings of the second and third formants are derived. The first formant pulse train is derived by establishing N signal level bands, where N is an integer at least equal to two. Adjacent ones of the signal bands have common boundaries, each of which is a predetermined percentage of the peak level of a complete cycle of the speech waveform.
The implementation of a programmable microprocessor for real time speech processing is described. The design of a fast special-purpose computer operating at 150 nsec per instruction time reduces the problem of speech encoding and decoding to a software problem. Each instruction is a twelve-bit word, and the information conveyed by a word is explained. The microprocessor is controlled by two clocks - the A/D clock, or input sampling clock, which loads the digital input into the input register and presets the counter to a value set by the external switches; and the instruction clock, or system clock, which operates at 6 MHz. At this system clock rate and a sampling clock rate of 30 KHz, 200 instructions can be executed between samples, and for many speech encoding and decoding algorithms, 200 instructions are more than enough. The microcomputer is being used to test various delta modulator encoding algorithms.
The relationship between the internal noise environment of helicopters and the ability of personnel to understand commands and instructions was studied. A test program was conducted to relate speech intelligibility to a standard measurement called Articulation Index. An acoustical simulator was used to provide noise environments typical of Army helicopters. Speech material (command sentences and phonetically balanced word lists) were presented at several voice levels in each helicopter environment. Recommended helicopter internal noise criteria, based on speech communication, were derived and the effectiveness of hearing protection devices were evaluated.
Intelligibility of PB word lists embedded in simultaneous masking noise was evaluated before and after fatiguing-noise exposure, which was determined by observing the number of words correctly repeated during a shadowing task. Both the speech signal and the masking noise were filtered to a 2825-3185-Hz band. Masking-noise leves were varied from 0- to 90-dB SL. Fatigue was produced by a 1500-3000-Hz octave band of noise at 115 dB (re 20 micron-Pa) presented continuously for 5 min. The results of three experiments indicated that speed intelligibility was reduced when the speech was presented against a background of silence but that the fatiguing-noise exposure had no effect on intelligibility when the speech was made more intense and embedded in masking noise of 40-90-dB SL. These observations are interpreted by considering the recruitment produced by fatigue and masking noise.
The Versatile Portable Speech Prosthesis (VPSP), a synthetic speech output communication aid for non-speaking people is described. It was intended initially for severely physically limited people with cerebral palsy who are in electric wheelchairs. Hence, it was designed to be placed on a wheelchair and powered from a wheelchair battery. It can easily be separated from the wheelchair. The VPSP is versatile because it is designed to accept any means of single switch, multiple switch, or keyboard control which physically limited people have the ability to use. It is portable because it is mounted on and can go with the electric wheelchair. It is a speech prosthesis, obviously, because it speaks with a synthetic voice for people unable to speak with their own voices. Both hardware and software are described.
Compact speech synthesizer useful traveling companion to speech-handicapped. User simply enters statement on board, and synthesizer converts statement into spoken words. Battery-powered and housed in briefcase, easily carried on trips. Unit used on telephones and face-to-face communication. Synthesizer consists of micro-computer with memory-expansion module, speech-synthesizer circuit, batteries, recharger, dc-to-dc converter, and telephone amplifier. Components, commercially available, fit neatly in 17-by 13-by 5-in. briefcase. Weighs about 20 lb (9 kg) and operates and recharges from ac receptable.
A speech compression project has recently been completed to develop a speech coding algorithm suitable for operation in a mobile satellite environment aimed at providing telephone quality natural speech at 4.8 kbps. The work has resulted in two alternative techniques which achieve reasonably good communications quality at 4.8 kbps while tolerating vehicle noise and rather severe channel impairments. The algorithms are embodied in a compact self-contained prototype consisting of two AT and T 32-bit floating-point DSP32 digital signal processors (DSP). A Motorola 68HC11 microcomputer chip serves as the board controller and interface handler. On a wirewrapped card, the prototype's circuit footprint amounts to only 200 sq cm, and consumes about 9 watts of power.
The value of speech controls in a dual-task experiment that also evaluated asymmetric transfer effects is considered. There was no evidence of asymmetric transfer in spite of significant effects supporting the advantage of mixing manual and speech responses. The data suggest that speech controls can be used to enhance performance in operational multiple-task environments.
Vector adaptive/predictive technique for digital encoding of speech signals yields decoded speech of very good quality after transmission at coding rate of 9.6 kb/s and of reasonably good quality at 4.8 kb/s. Requires 3 to 4 million multiplications and additions per second. Combines advantages of adaptive/predictive coding, and code-excited linear prediction, yielding speech of high quality but requires 600 million multiplications and additions per second at encoding rate of 4.8 kb/s. Vector adaptive/predictive coding technique bridges gaps in performance and complexity between adaptive/predictive coding and code-excited linear prediction.
This issue of the Index to NASA News Releases and Speeches contains a listing of news releases distributed by the Office of Public Affairs, NASA Headquarters, and a selected listing of speeches presented by members of the Headquarters staff during 1986. The index is arranged in six sections: Subject Index, Personal Names Index, News Release Number Index, Accession Number Index, and Speeches and News Releases.
This issue of the Index to NASA News Releases and Speeches contains a listing of news releases distributed by the Office of Public Affairs, NASA Headquarters, and a selected listing of speeches presented by members of the Headquarters staff during 1987. The index is arranged in six sections: Subject Index, Personal Names Index, News Release Number Index, Accession Number Index, and Speeches and News Releases.
This issue of the Index to NASA News Releases and Speeches contains a listing of news releases distributed by the Office of Public Affairs, NASA Headquarters, and a selected listing of speeches presented by members of the Headquarters staff during 1988. The index is arranged in six sections: Subject Index, Personal Names Index, News Release Number Index, Accession Number Index, and Speeches and News Releases.