09-03-2011, 11:23 AM
[attachment=9845]
SPEECH-RECOGNITION AND SPEECH SYNTHESIS
1. ABSTRACT
Astronauts exploring Moon will probably want to use computers in the field for many purposes including communication such as e- mail, information retrieval, and command and control of both their spacesuit and off- suit equipment. Traditional computer systems present many difficulties in the field including the difficulty of operating a keyboard wearing a spacesuit and the effect of pervasive dust and extreme conditions on equipment. Speech-recognition and speech synthesis have been proposed as partial solutions for these problems.
Methods for creating a controlled acoustic environment in a spacesuit so that current large vocabulary, speaker-dependent speech-recognition can be used reliably are discussed. Display options such as in-helmet displays, external projectors, and external flat screens are discussed. The advantages and challenges of in-helmet displays are detailed. Pointing devices such as trackballs and motion sensors that can be integrated into a spacesuit are discussed for operating graphical applications and traditional graphical user interfaces. User interface and operating system design with no keyboard, no mouse, and no traditional graphical user interface is discussed.
Partitioning applications between fast, high reliability physical input devices -- switches, buttons, motion and pointing sensors -- and slower, less reliable, more flexible and versatile speech input is discussed. In general, mission-critical and life-support functions will use physical inputs. Lower priority and support functions such as e- mail, database query, and non-essential equipment control will use speech. What can and cannot be done in space exploration applications with current accuracy large vocabulary speech-recognition (about 95% accurate) is discussed. Some strategies to increase accuracy such as incorporating syntactic and semantic rules are discussed.
2. INTRODUCTION
The planet Mars has been proposed as the next major step in the human exploration of space after the Moon. Mars has a diameter of 4219 miles. Mars has a surface area of 144 million square kilometers, about the same as all the continents and islands of earth put together. This is about 28% of total surface area of the Earth -- including the oceans. The surface gravity of Mars is 38% of the surface gravity on Earth. Mars traverses a slightly elliptical orbit around the sun ranging from 128,000,000 miles to 155,000,000 miles from the Sun. Mars has an axial tilt of 25.2°. The Martian day is 24 hours and 37 minutes. The Martian year is 687 days.
The average surface temperature of Mars is -85°F. The Martian atmosphere is about 1% he atmospheric pressure at sea level on Earth. It is comparable in density and pressure to he atmosphere on Earth at an altitude of 100,000 feet. The Martian atmosphere is 95% carbon dioxide, 3% nitrogen, and 2% other gasses. Mars receives about half the sunlight hat the Earth receives. However, lacking the Earth's heavy atmosphere and ozone layer, ars receives more ultraviolet light than the Earth at its surface. Mars lacks the global magnetic field that protects the Earth from cosmic rays.
Current proposals for humans to Mars usually involve a lengthy mission using chemical ockets1. About 180 days will be spent traveling from Earth to Mars. Often, a lengthy tay, such as 550 days, on the planet Mars is envisioned. An additional 180 days will be spent traveling back from Mars to Earth.
3. Goals for the Human Exploration of Mars
Goals for the human exploration of Mars include the search for past or present life on the planet. Astronauts will also seek resources, especially easily exploitable resources. Possible resources include mineral deposits (especially surface mineral deposits), water, and methane. Recent observations have produced evidence of subsurface water or ice on Mars. Trace amounts of methane have recently been reported in the Martian atmosphere. On Earth, most methane is attributed to past or present life. Methane is the principal ingredient of natural gas on Earth. Methane is both a fuel and a precursor to plastics and other materials in industrial processes. Methane can also be used as rocket fuel. As fluids, both water and methane do not require extensive heavy mining equipment to exploit on Mars.
Surface features of interest in the exploration of Mars include OphirChasma, Juventae Chasma, Hebes Chasma, Kasei Vallis, and the Viking 1 landing site, and many other locations on the planet. A thorough exploration of the planet will require that the astronauts visit many locations separated by thousands of kilometers, using a vehicle such as a rover or rocket plane.
prepared by:
Aditi.P
Swathi.Ch
[attachment=9846]
Abstract:
Language is man's most important means of communication and speech its primary medium. Speech provides an international forum for communication among researchers in the disciplines that contribute to our understanding of the production, perception, processing, learning and use. Spoken interaction both between human interlocutors and between humans and machines is inescapably embedded in the laws and conditions of Communication, which comprise the encoding and decoding of meaning as well as the mere transmission of messages over an acoustical channel. Here we deal with this interaction between the man and machine through synthesis and recognition applications.
The paper dwells on the speech technology and conversion of speech into analog and digital waveforms which is understood by the machines
Speech recognition, or speech-to-text, involves capturing and digitizing the sound waves, converting them to basic language units or phonemes, constructing words from phonemes, and contextually analyzing the words to ensure correct spelling for words that sound alike. Speech Recognition is the ability of a computer to recognize general, naturally flowing utterances from a wide variety of users. It recognizes the caller's answers to move along the flow of the call.
We have emphasized on the modeling of speech units and grammar on the basis of Hidden Markov Model. Speech Recognition allows you to provide input to an application with your voice. The applications and limitations on this subject has enlightened us upon the impact of speech processing in our modern technical field.
While there is still much room for improvement, current speech recognition systems have remarkable performance. We are only humans, but as we develop this technology and build remarkable changes we attain certain achievements. Rather than asking what is still deficient, we ask instead what should be done to make it efficient….
INTRODUCTION
One of the most important inventions of the nineteenth century was the telephone. Then at the midpoint of twentieth century, the invention of the digital computer amplified the power of our minds, enabled us to think and work more efficiently and made us more imaginative then we could ever have imagined .now several new technologies have empowered us to teach computers to talk to us in our native languages and to listen to us when we speak(recognition); haltingly computers have begun to understand what we say. Having given our computers both oral and aural abilities, we have been able to produce innumerable computer applications that further enhance our productivity. Such capabilities enable us to route phone calls automatically and to obtain and update computer based information by telephone, using a group of activities collectively referred to as Voice Processing.
SPEECH TECHNOLOGY
Three primary speech technologies are used in voice processing applications: stored speech, text-to – speech and speech recognition . Stored speech involves the production of computer speech from an actual human voice that is stored in a computer’s memory and used in any of several ways.
Speech can also be synthesized from plain text in a process known as text-to – speech which also enables voice processing applications to read from textual database.
Speech recognition is the process of deriving either a textual transcription or some form of meaning from a spoken input.
Speech analysis can be thought of as that part of voice processing that converts human speech to digital forms suitable for transmission or storage by computers.
Speech synthesis functions are essentially the inverse of speech analysis – they reconvert speech data from a digital form to one that’s similar to the original recording and suitable for playback.
Speech analysis processes can also be referred to as a digital speech encoding ( or simply coding) and
DIGITIZATION OF ANALOG WAVEFORMS
Two processes are required to digitize an analog signal:
(a) Sampling which discretizes the signal in time
(b) Quantizing, which discretizes the signal in amplitude.
ANALYSIS/SYNTHESIS IN THE TIME AND FREQUENCY DOMAIN
The analog and digital speech waveforms exist in time domain; the waveform represents speech as amplitude versus time. The time –domain sound pressure wave emanating from the lips is easily converted by microphone to a speech waveform, so it’s natural that speech analysis/synthesis systems operate directly upon this waveform. The objective of every speech-coding scheme is to produce code of minimum data rate so that a synthesizer can reconstruct an accurate facsimile of the original speech waveform. Frequency domain coders attempt to reach this objective by exploiting the resonant characteristics of the vocal tract.
VOCODERS – Voice Coders
RELP – Residual–excited linear production
SBC – Subband Coding
CVSD- Continously variable slope deltmodulation
ADM - Adaptive Delta Modulation
ADPCM – Adaptive Quantization
LOG PCM – Logarithmic Quantization
Figure summarizes the relative voice quality of various speech coders. Voice quality is measured in terms of signal-to-noise ratio on the y-axis versus data rate as a logarithmic scale on the x-axis. Both solid and dashed traces appear in the figure and respectively represent objective and estimated results- all of which are approximations.
SPEECH RECOGNITION
Speech recognition is the process of deriving either a textual transcription or some form of meaning from a spoken input. Speech recognition is the inverse process of synthesis, conversion of speech to text. The Speech recognition task is complex. This involves the computer taking the user's speech and interpreting what has been said. This allows the user to control the computer (or certain aspects of it) by voice, rather than having to use the mouse and keyboard, or alternatively just dictating the contents of a document. It would be complicated enough if every speaker pronounced every word in an identical manner each time, but this doesn’t happen
SPEECH-RECOGNITION AND SPEECH SYNTHESIS
1. ABSTRACT
Astronauts exploring Moon will probably want to use computers in the field for many purposes including communication such as e- mail, information retrieval, and command and control of both their spacesuit and off- suit equipment. Traditional computer systems present many difficulties in the field including the difficulty of operating a keyboard wearing a spacesuit and the effect of pervasive dust and extreme conditions on equipment. Speech-recognition and speech synthesis have been proposed as partial solutions for these problems.
Methods for creating a controlled acoustic environment in a spacesuit so that current large vocabulary, speaker-dependent speech-recognition can be used reliably are discussed. Display options such as in-helmet displays, external projectors, and external flat screens are discussed. The advantages and challenges of in-helmet displays are detailed. Pointing devices such as trackballs and motion sensors that can be integrated into a spacesuit are discussed for operating graphical applications and traditional graphical user interfaces. User interface and operating system design with no keyboard, no mouse, and no traditional graphical user interface is discussed.
Partitioning applications between fast, high reliability physical input devices -- switches, buttons, motion and pointing sensors -- and slower, less reliable, more flexible and versatile speech input is discussed. In general, mission-critical and life-support functions will use physical inputs. Lower priority and support functions such as e- mail, database query, and non-essential equipment control will use speech. What can and cannot be done in space exploration applications with current accuracy large vocabulary speech-recognition (about 95% accurate) is discussed. Some strategies to increase accuracy such as incorporating syntactic and semantic rules are discussed.
2. INTRODUCTION
The planet Mars has been proposed as the next major step in the human exploration of space after the Moon. Mars has a diameter of 4219 miles. Mars has a surface area of 144 million square kilometers, about the same as all the continents and islands of earth put together. This is about 28% of total surface area of the Earth -- including the oceans. The surface gravity of Mars is 38% of the surface gravity on Earth. Mars traverses a slightly elliptical orbit around the sun ranging from 128,000,000 miles to 155,000,000 miles from the Sun. Mars has an axial tilt of 25.2°. The Martian day is 24 hours and 37 minutes. The Martian year is 687 days.
The average surface temperature of Mars is -85°F. The Martian atmosphere is about 1% he atmospheric pressure at sea level on Earth. It is comparable in density and pressure to he atmosphere on Earth at an altitude of 100,000 feet. The Martian atmosphere is 95% carbon dioxide, 3% nitrogen, and 2% other gasses. Mars receives about half the sunlight hat the Earth receives. However, lacking the Earth's heavy atmosphere and ozone layer, ars receives more ultraviolet light than the Earth at its surface. Mars lacks the global magnetic field that protects the Earth from cosmic rays.
Current proposals for humans to Mars usually involve a lengthy mission using chemical ockets1. About 180 days will be spent traveling from Earth to Mars. Often, a lengthy tay, such as 550 days, on the planet Mars is envisioned. An additional 180 days will be spent traveling back from Mars to Earth.
3. Goals for the Human Exploration of Mars
Goals for the human exploration of Mars include the search for past or present life on the planet. Astronauts will also seek resources, especially easily exploitable resources. Possible resources include mineral deposits (especially surface mineral deposits), water, and methane. Recent observations have produced evidence of subsurface water or ice on Mars. Trace amounts of methane have recently been reported in the Martian atmosphere. On Earth, most methane is attributed to past or present life. Methane is the principal ingredient of natural gas on Earth. Methane is both a fuel and a precursor to plastics and other materials in industrial processes. Methane can also be used as rocket fuel. As fluids, both water and methane do not require extensive heavy mining equipment to exploit on Mars.
Surface features of interest in the exploration of Mars include OphirChasma, Juventae Chasma, Hebes Chasma, Kasei Vallis, and the Viking 1 landing site, and many other locations on the planet. A thorough exploration of the planet will require that the astronauts visit many locations separated by thousands of kilometers, using a vehicle such as a rover or rocket plane.
prepared by:
Aditi.P
Swathi.Ch
[attachment=9846]
Abstract:
Language is man's most important means of communication and speech its primary medium. Speech provides an international forum for communication among researchers in the disciplines that contribute to our understanding of the production, perception, processing, learning and use. Spoken interaction both between human interlocutors and between humans and machines is inescapably embedded in the laws and conditions of Communication, which comprise the encoding and decoding of meaning as well as the mere transmission of messages over an acoustical channel. Here we deal with this interaction between the man and machine through synthesis and recognition applications.
The paper dwells on the speech technology and conversion of speech into analog and digital waveforms which is understood by the machines
Speech recognition, or speech-to-text, involves capturing and digitizing the sound waves, converting them to basic language units or phonemes, constructing words from phonemes, and contextually analyzing the words to ensure correct spelling for words that sound alike. Speech Recognition is the ability of a computer to recognize general, naturally flowing utterances from a wide variety of users. It recognizes the caller's answers to move along the flow of the call.
We have emphasized on the modeling of speech units and grammar on the basis of Hidden Markov Model. Speech Recognition allows you to provide input to an application with your voice. The applications and limitations on this subject has enlightened us upon the impact of speech processing in our modern technical field.
While there is still much room for improvement, current speech recognition systems have remarkable performance. We are only humans, but as we develop this technology and build remarkable changes we attain certain achievements. Rather than asking what is still deficient, we ask instead what should be done to make it efficient….
INTRODUCTION
One of the most important inventions of the nineteenth century was the telephone. Then at the midpoint of twentieth century, the invention of the digital computer amplified the power of our minds, enabled us to think and work more efficiently and made us more imaginative then we could ever have imagined .now several new technologies have empowered us to teach computers to talk to us in our native languages and to listen to us when we speak(recognition); haltingly computers have begun to understand what we say. Having given our computers both oral and aural abilities, we have been able to produce innumerable computer applications that further enhance our productivity. Such capabilities enable us to route phone calls automatically and to obtain and update computer based information by telephone, using a group of activities collectively referred to as Voice Processing.
SPEECH TECHNOLOGY
Three primary speech technologies are used in voice processing applications: stored speech, text-to – speech and speech recognition . Stored speech involves the production of computer speech from an actual human voice that is stored in a computer’s memory and used in any of several ways.
Speech can also be synthesized from plain text in a process known as text-to – speech which also enables voice processing applications to read from textual database.
Speech recognition is the process of deriving either a textual transcription or some form of meaning from a spoken input.
Speech analysis can be thought of as that part of voice processing that converts human speech to digital forms suitable for transmission or storage by computers.
Speech synthesis functions are essentially the inverse of speech analysis – they reconvert speech data from a digital form to one that’s similar to the original recording and suitable for playback.
Speech analysis processes can also be referred to as a digital speech encoding ( or simply coding) and
DIGITIZATION OF ANALOG WAVEFORMS
Two processes are required to digitize an analog signal:
(a) Sampling which discretizes the signal in time
(b) Quantizing, which discretizes the signal in amplitude.
ANALYSIS/SYNTHESIS IN THE TIME AND FREQUENCY DOMAIN
The analog and digital speech waveforms exist in time domain; the waveform represents speech as amplitude versus time. The time –domain sound pressure wave emanating from the lips is easily converted by microphone to a speech waveform, so it’s natural that speech analysis/synthesis systems operate directly upon this waveform. The objective of every speech-coding scheme is to produce code of minimum data rate so that a synthesizer can reconstruct an accurate facsimile of the original speech waveform. Frequency domain coders attempt to reach this objective by exploiting the resonant characteristics of the vocal tract.
VOCODERS – Voice Coders
RELP – Residual–excited linear production
SBC – Subband Coding
CVSD- Continously variable slope deltmodulation
ADM - Adaptive Delta Modulation
ADPCM – Adaptive Quantization
LOG PCM – Logarithmic Quantization
Figure summarizes the relative voice quality of various speech coders. Voice quality is measured in terms of signal-to-noise ratio on the y-axis versus data rate as a logarithmic scale on the x-axis. Both solid and dashed traces appear in the figure and respectively represent objective and estimated results- all of which are approximations.
SPEECH RECOGNITION
Speech recognition is the process of deriving either a textual transcription or some form of meaning from a spoken input. Speech recognition is the inverse process of synthesis, conversion of speech to text. The Speech recognition task is complex. This involves the computer taking the user's speech and interpreting what has been said. This allows the user to control the computer (or certain aspects of it) by voice, rather than having to use the mouse and keyboard, or alternatively just dictating the contents of a document. It would be complicated enough if every speaker pronounced every word in an identical manner each time, but this doesn’t happen
