Search NASA⌕ Search

SEARCH · Search NASA

Results for “Speech”

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.

At least 199 records · Page 11
All sourcesNASA NTRSDOE OSTI
NASA NTRS2018

Considerations for Implementing Voice-Controlled Spacecraft Systems Through a Human-Centered Design Approach

As computational power and speech recognition algorithms improve, the consumer market will see better-performing speech recognition applications. The cell phone and Internet-related service industry have further enhanced speech recognition applications using artificial intelligence and statistical data-mining techniques. These improvements to speech recognition technology (SRT) may one day help astronauts on future deep space human missions that require control of complex spacecraft systems or spacesuit applications by voice. Though SRT and more advanced speech recognition techniques show promise, use of this technology for a space application such as vehicle/habitat/spacesuit requires careful considerations. There are still recognition challenges to overcome such as background noise, human speech variability, and task loading. However, implemented correctly, a voice-controlled spacecraft system (VCSS) can provide a useful, natural and efficient form of human-machine communications during complex tasks such as when the hands and eyes are busy or as an aid for vehicle situational awareness inquiries or collaborative human-robot tasks. This document provides considerations and guidance for the use of SRT in VCSS applications for space missions, specifically in command-and-control (C2) applications where the commanding is user-initiated. First, current SRT limitations as known at the time of this report are given. Then, highlights of SRT used in the space program provide the reader with a history of some of the human spaceflight applications and research. Next, an overview of the speech production process and the intrinsic variations of speech are provided. Finally, general guidance and considerations are given for development of a VCSS using a human-centered design approach for space applications that includes vocabulary selection and performance testing, as well as VCSS considerations for C2 dialogue management design, feedback, error handling, and evaluation/usability testing. Available from

Salazar, George A.↗
NASA NTRS1981

Evaluation of synthesized voice approach callouts /SYNCALL/

The two basic approaches to the generation of 'synthesized' speech include a utilization of analog recorded human speech and a construction of speech entirely from algorithms applied to constants describing speech sounds. Given the availability of synthesized speech displays for man-machine systems, research is needed to study suggested applications for speech and design principles for speech displays. The present investigation is concerned with a study for which new performance measures were developed. A number of air carrier approach and landing accidents during low or impaired visibility have been associated with the absence of approach callouts. The study had the purpose to compare a pilot-not-flying (PNF) approach callout system to a system composed of PNF callouts augmented by an automatic synthesized voice callout system (SYNCALL). Pilots were found to favor the use of a SYNCALL system containing certain modifications.

Simpson, C. A.↗
NASA NTRS1986

Crew Communication as a Factor in Aviation Accidents

The crew communication process is analyzed. Planning and explanation are shown to be well-structured discourse types, described by formal rules. These formal rules are integrated with those describing the other most important discourse type within the cockpit: the command-and-control speech act chain. The latter is described as a sequence of speech acts for making requests (including orders and suggestions), for making reports, for supporting or challenging statements, and for acknowledging previous speech acts. Mitigation level, a linguistic indication of indirectness and tentativeness in speech, was an important variable in several hypotheses, i.e., the speech of subordinates is more mitigated than the speech of superiors, the speech of all crewmembers is less mitigated when they know that they are in either a problem or emergency situation, and mitigation is a factor in failures of crewmembers to initiate discussion of new topics or have suggestions ratified by the captain. Test results also show that planning and explanation are more frequently performed by captains, are done more during crew- recognized problems, and are done less during crew-recognized emergencies. The test results also indicated that planning and explanation are more frequently performed by captains than by other crewmembers, are done more during crew-recognized problems, and are done less during-recognized emergencies.

Goguen, J.↗
NASA NTRS1988

Voice control of complex workstations

The use of a speaker-dependent connected word recognition system to control an Air Traffic Control (ATC) demonstration workstation is described, also the work that went into developing that speech system. The workstation with speech recognition was demonstrated live at an Air Traffic Controller's Association convention in 1987. The purpose of the demonstration workstation is discussed, with the development of the speech interface highlighted. Included are: a brief description of the speech hardware and software, and overview of the speech driven workstation functions, a description of the speech vocabulary/grammer, and details that the enrollment and training procedures used in preparing the controllers for the demonstrations. Although no quantitative results are available, the potential benefits of using voice as an interface to this type of workstation are discussed and limitations of current speech technology and areas where more work is required are highlighted.

Scruggs, Jeffrey L.↗
NASA NTRS2000

Noise Reduction using Frequency Sub-Band Adaptive Spectral Subtraction

A frequency sub-band based adaptive spectral subtraction algorithm is developed to remove noise from noise-corrupted speech signals. A single microphone is used to obtain both the noise-corrupted speech and the estimate of the statistics of the noise. The statistics of the noise are estimated during time frames that do not contain speech. These statistics are used to determine if future time frames contain speech. During speech time frames, the algorithm determines which frequency sub-bands contain useful speech information and which frequency sub-bands contain only noise. The frequency sub-bands, which contain only noise, are subtracted off at a larger proportion so the noise does not compete with the speech information. Simulation results are presented.

Kozel, David↗
NASA NTRS2019

Development Considerations for Implementing a Voice-Controlled Spacecraft System

As computational power and speech recognition algorithms improve, the consumer market will see better-performing speech recognition applications. The cell phone and Internet-related service industry have further enhanced speech recognition applications using artificial intelligence and statistical data-mining techniques. These improvements to speech recognition technology (SRT) may one day help astronauts on future deep space human missions that require control of complex spacecraft systems or spacesuit applications by voice. Though SRT and more advanced speech recognition techniques show promise, use of this technology for a space application such as vehicle/habitat/spacesuit requires careful considerations. This paper provides considerations and guidance for the use of SRT in voice-controlled spacecraft systems (VCSS) applications for space missions, specifically in command-and-control (C2) applications where the commanding is user-initiated. First, current SRT limitations as known at the time of this report are given. Then, highlights of SRT used in the space program provide the reader with a history of some of the human spaceflight applications and research. Next, an overview of the speech production process and the intrinsic variations of speech are provided. Finally, general guidance and considerations are given for the development of a VCSS using a human-centered design approach for space applications that includes vocabulary selection and performance testing, as well as VCSS considerations for C2 dialogue management design, feedback, error handling, and evaluation/usability testing.

Salazar, George↗
NASA NTRS1988

Quantile Vocoder

Parameters of spectral envelope obtained statistically. Algorithm for digital compression of speech signals encodes power spectral density of each short interval of speech by use of quantiles or order statistics. Purpose to reduce bit rate and bandwidth required for transmission. When fully developed, quantile vocoder - speech-encoding system based on new algorithm - expected moderately complicated compared with other speech-encoding systems and reproduce high-quality speech from code transmitted at relatively low bit rates. Speech signal treated mathematically as though amplitude spectrum stationary during short coding intervals, called "windows". Window duration of 20 or 35 ms, chosen as compromise between frequency resolution and time resolution. During each window, short-time amplitude and power spectra found by sampling at high rate (typically 10 kHz) and taking fast Fourier transforms (FFT's).

Swaminathan, Kumar↗
NASA NTRS1993

A high quality voice coder with integrated echo canceller and voice activity detector for mobile satellite applications

In the last decade, low bit rate speech coding research has received much attention resulting in newly developed, good quality, speech coders operating at as low as 4.8 Kb/s. Although speech quality at around 8 Kb/s is acceptable for a wide variety of applications, at 4.8 Kb/s more improvements in quality are necessary to make it acceptable to the majority of applications and users. In addition to the required low bit rate with acceptable speech quality, other facilities such as integrated digital echo cancellation and voice activity detection are now becoming necessary to provide a cost effective and compact solution. In this paper we describe a CELP speech coder with integrated echo canceller and a voice activity detector all of which have been implemented on a single DSP32C with 32 KBytes of SRAM. The quality of CELP coded speech has been improved significantly by a new codebook implementation which also simplifies the encoder/decoder complexity making room for the integration of a 64-tap echo canceller together with a voice activity detector.

Kondoz, A. M.↗
NASA NTRS1987

Space station interior noise analysis program

Documentation is provided for a microcomputer program which was developed to evaluate the effect of the vibroacoustic environment on speech communication inside a space station. The program, entitled Space Station Interior Noise Analysis Program (SSINAP), combines a Statistical Energy Analysis (SEA) prediction of sound and vibration levels within the space station with a speech intelligibility model based on the Modulation Transfer Function and the Speech Transmission Index (MTF/STI). The SEA model provides an effective analysis tool for predicting the acoustic environment based on proposed space station design. The MTF/STI model provides a method for evaluating speech communication in the relatively reverberant and potentially noisy environments that are likely to occur in space stations. The combinations of these two models provides a powerful analysis tool for optimizing the acoustic design of space stations from the point of view of speech communications. The mathematical algorithms used in SSINAP are presented to implement the SEA and MTF/STI models. An appendix provides an explanation of the operation of the program along with details of the program structure and code.

Stusnick, E.↗
NASA NTRS1988

Analysis and improvement of the vector quantization in SELP (Stochastically Excited Linear Prediction)

The Stochastically Excited Linear Prediction (SELP) algorithm is described as a speech coding method employing a two-stage vector quantization. The first stage uses an adaptive codebook which efficiently encodes the periodicity of voiced speech, and the second stage uses a stochastic codebook to encode the remainder of the excitation signal. The adaptive codebook performs well when the pitch period of the speech signal is larger than the frame size. An extension is introduced, which increases its performance for the case that the frame size is longer than the pitch period. The performance of the stochastic stage, which improves with frame length, is shown to be best in those sections of the speech signal where a high level of short-term correlations is present. It can be concluded that the SELP algorithm performs best during voiced speech where the pitch period is longer than the frame length.

Kleijn, W. B.↗
NASA NTRS2006

Are You Talking to Me? Dialogue Systems Supporting Mixed Teams of Humans and Robots

This position paper describes an approach to building spoken dialogue systems for environments containing multiple human speakers and hearers, and multiple robotic speakers and hearers. We address the issue, for robotic hearers, of whether the speech they hear is intended for them, or more likely to be intended for some other hearer. We will describe data collected during a series of experiments involving teams of multiple human and robots (and other software participants), and some preliminary results for distinguishing robot-directed speech from human-directed speech. The domain of these experiments is Mars-analogue planetary exploration. These Mars-analogue field studies involve two subjects in simulated planetary space suits doing geological exploration with the help of 1-2 robots, supporting software agents, a habitat communicator and links to a remote science team. The two subjects are performing a task (geological exploration) which requires them to speak with each other while also speaking with their assistants. The technique used here is to use a probabilistic context-free grammar language model in the speech recognizer that is trained on prior robot-directed speech. Intuitively, the recognizer will give higher confidence to an utterance if it is similar to utterances that have been directed to the robot in the past.

Dowding, John↗
NASA NTRS2009

Processing Electromyographic Signals to Recognize Words

A recently invented speech-recognition method applies to words that are articulated by means of the tongue and throat muscles but are otherwise not voiced or, at most, are spoken sotto voce. This method could satisfy a need for speech recognition under circumstances in which normal audible speech is difficult, poses a hazard, is disturbing to listeners, or compromises privacy. The method could also be used to augment traditional speech recognition by providing an additional source of information about articulator activity. The method can be characterized as intermediate between (1) conventional speech recognition through processing of voice sounds and (2) a method, not yet developed, of processing electroencephalographic signals to extract unspoken words directly from thoughts. This method involves computational processing of digitized electromyographic (EMG) signals from muscle innervation acquired by surface electrodes under a subject's chin near the tongue and on the side of the subject s throat near the larynx. After preprocessing, digitization, and feature extraction, EMG signals are processed by a neural-network pattern classifier, implemented in software, that performs the bulk of the recognition task as described.

Jorgensen, C. C.↗
NASA NTRS1972

Transmission line inversion and synthesis from the point of view of transient response

The transmission line inversion problem is applied to the speech communication process. The problem involves acquiring information necessary for synthesis of speech and for making models of the speech production mechanism. Formulation for the problem is derived from an analysis of the human vocal tract functions. It is known that speech sounds are produced by acoustic excitation of the tract by means of quasi-periodic pulses from the vocal cords during vowel sounds and turbulent air flow at various points along the tract during fricative sounds. By assuming plane wave propagation, differential equations are obtained relating the cross sectional area of the tract, the pressure, and the volume velocity. By replacing the pressure factor with a voltage factor and the volume velocity by current, the problem becomes a transmission line problem.

Sondhi, M. M.↗
NASA NTRS1974

The design of a device for hearer and feeler differentiation, part A

A speech modulated white noise device is reported that gives the rhythmic characteristics of a speech signal for intelligible reception by deaf persons. The signal is composed of random amplitudes and frequencies as modulated by the speech envelope characteristics of rhythm and stress. Time intensity parameters of speech are conveyed through the vibro-tactile sensation stimuli.

Creecy, R.↗
NASA NTRS1977

Adaptation to delayed auditory feedback

Delayed auditory feedback disrupts the production of speech, causing an increase in speech duration as well as many articulatory errors. To determine whether prolonged exposure to delayed auditory feedback (DAF) leads to adaptive compensations in speech production, 10 subjects were exposed in separate experimental sessions to both incremental and constant-delay exposure conditions. Significant adaptation occurred for syntactically structured stimuli in the form of increased speaking rates. After DAF was removed, aftereffects were apparent for all stimulus types in terms of increased speech rates. A carry-over effect from the first to the second experimental session was evident as long as 29 days after the first session. The use of strategies to overcome DAF and the differences between adaptation to DAF and adaptation to visual rearrangement are discussed.

Katz, D. I.↗
NASA NTRS1988

Intelligent interfaces for expert systems

Vital to the success of an expert system is an interface to the user which performs intelligently. A generic intelligent interface is being developed for expert systems. This intelligent interface was developed around the in-house developed Expert System for the Flight Analysis System (ESFAS). The Flight Analysis System (FAS) is comprised of 84 configuration controlled FORTRAN subroutines that are used in the preflight analysis of the space shuttle. In order to use FAS proficiently, a person must be knowledgeable in the areas of flight mechanics, the procedures involved in deploying a certain payload, and an overall understanding of the FAS. ESFAS, still in its developmental stage, is taking into account much of this knowledge. The generic intelligent interface involves the integration of a speech recognizer and synthesizer, a preparser, and a natural language parser to ESFAS. The speech recognizer being used is capable of recognizing 1000 words of connected speech. The natural language parser is a commercial software package which uses caseframe instantiation in processing the streams of words from the speech recognizer or the keyboard. The systems configuration is described along with capabilities and drawbacks.

Villarreal, James A.↗
NASA NTRS1990

A 4800 bps CELP vocoder with an improved excitation

The Stochastic or Code Excited Linear Predictive Coder (CELP) is among the promising candidates for producing good quality speech at low bit rates. However, the speech quality produced suffers from perceived roughness. Many researchers have used pole-zero postfilters to mask the roughness at the output of the synthesis filter. Although the postfilters are effective in masking the noise at low bit rates, they produce spectral distortions. It is proposed that speech can be improved by introducing two modifications to the fixed stochastic codebook. In the first modification, the stochastic codebook is used only when the long term correlations are low. Otherwise, a pulse like codebook is selected. In the second modification, the selected codebook output is weighted using an adaptive spectral shaping procedure. These two modifications were incorporated in a 4800 bps CELP coder and have resulted in a perceptually improved vocoded speech.

Hassanein, Hisham↗
NASA NTRS1990

A low-delay 8 Kb/s backward-adaptive CELP coder

Code excited linear prediction coding is an efficient technique for compressing speech sequences. Communications quality of speech can be obtained at bit rates below 8 Kb/s. However, relatively large coding delays are necessary to buffer the input speech in order to perform the LPC analysis. A low delay 8 Kb/s CELP coder is introduced in which the short term predictor is based on past synthesized speech. A new distortion measure that improves the tracking of the formant filter is discussed. Formal listening tests showed that the performance of the backward adaptive coder is almost as good as the conventional CELP coder.

Neumeyer, L. G.↗