Abstract of this computer paper-presentations : (Speech Recognition)
This paper deals with the topic SPEECH RECOGNITION which can make a revolution in the years to come. Speech recognition acts as an interface between the user and the system. Its applications vary to the extent that it is a successful replacement for input devices like Keyboard ,mouse etc. This paper contains information about Automatic Speech Recognition which decodes speech signals to phones, which is the basic building block of any word. Speech Recognition Systems are classified as Dependent and Independent Systems. Dependent systems recognize the sound generated by a single speaker whereas an Independent System recognizes sounds generated by multiple speakers. Based on the delivery of speech it is divided into two parts i.e. Isolated Word Systems and Continuous Speech Systems. An isolated-word system operates on single words at a time - requiring a pause between saying each word and a Continuous Speech System operates on speech in which words are connected together. There are several approaches to automatic speech recognition Acoustic-Phonetic, Artificial Intelligence and Pattern Recognition.
In this paper an experiment has been described, where the speech signal is converted into phonetics. These phones are combined together to form the word which is closest to the word spoken by the speaker and hence the recognition of the signal is successful. Graphs of few phones are shown in order to distinguish voiced and unvoiced sounds.
Speech recognition finds its major applications in the field of communication, access security, spontaneous data entry and artificial intelligence.
In the conclusion, the Speech Recognition systems has failed to give accurate result as the accent varies from one person to the other and also the other factors like environmental noise which makes significant contribution for the failure of such systems.
SPEECH RECOGNITION:
Introduction
Speech recognition technologies allow computers equipped with a source of sound input, such as a microphone, to interpret human speech, e.g., for transcription or as an alternative method of interacting with a computer Automatic Speech Recognition. Automatic speech recognition is the process by which a computer maps an acoustic speech signal to text. Automatic speech understanding is the process by which a computer maps an acoustic speech signal to some form of abstract meaning of the speech.
What does speaker dependent / adaptive / independent mean? A speaker dependent system is developed to operate for a single speaker. These systems are usually easier to develop, cheaper to buy and more accurate, but not as flexible as speaker adaptive or speaker independent systems.
A speaker independent system is developed to operate for any speaker of a particular type (e.g. American English). These systems are the most difficult to develop, most expensive and accuracy is lower than speaker dependent systems. However, they are more flexible.
A speaker adaptive system is developed to adapt its operation to the characteristics of new speakers. It's difficulty lies somewhere between speaker independent and speaker dependent systems.
What does small/medium/large/very-large vocabulary mean?
The size of vocabulary of a speech recognition system affects the complexity, processing requirements and the accuracy of the system. Some applications only require a few words (e.g. numbers only), others require very large dictionaries (e.g. dictation machines). There are no established definitions, however, try
What does continuous speech and isolated-word mean? An isolated-word system operates on single words at a time - requiring a pause between saying each word. This is the simplest form of recognition to perform because the end points are easier to find and the pronunciation of a word tends not affect others. Thus, because the occurrences of words are more consistent they are easier to recognize.
A continuous speech system operates on speech in which words are connected together, i.e. not separated by pauses. Continuous speech is more difficult to handle because of a variety of effects. First, it is difficult to find the start and end points of words. Another problem is "co articulation". The production of each phoneme is affected by the production of surrounding phonemes, and similarly the start and end of words are affected by the preceding and following words. The recognition of continuous speech is also affected by the rate of speech (fast speech tends to be harder).
The Process of Speech Recognition There are several approaches to automatic speech recognition:
• Acoustic-Phonetic -- This approach is based on the idea that all spoken words can be split up into a finite group of phonetic units. If all of these phonetic units can be characterized computationally, one should be able to figure out what phonetic units have been spoken, and then decode them into words.
• Pattern Recognition -- This approach uses a training algorithm to teach a recognizer about the patterns present in specific words. It is similar to the acoustic-phonetic approach, but rather than defining the patterns explicitly (as phonetic units), Hidden Markov Model(HMM) based pattern recognizer finds it's own set of patterns.
• Artificial Intelligence -- This approach mixes the previous two approaches by combining phonetic, syntactic, lexical, and/or semantic based analysis with pattern recognition.
The Basic Steps:
The process of voice recognition is typically divided into several well defined steps. Different systems vary on the nature of these steps, as well as how each step is implemented, but the most successful systems follow a similar methodology.
• Divide the sound wave into evenly spaced blocks
• Process each block for important characteristics, such as strength across various frequency ranges, number of zero crossings, and total energy.
• Using these characteristics, attempt to associate each block with a Phone, which is the most basic unit of speech, producing a string of phones.
• Find the word whose model is the most likely match to the string of phones which was produced.
The Experiment:
Numerous samples were take of various people saying either 'yes' or 'no'. This method is somewhat artificial in that a real system first has to detect whether speech exists at all (this problem is the separate task of speech detection). Therefore we implemented a criteria for the detection of speech. The method is also somewhat artificial, because in fluent speech, words tend to run together and the word boundaries are not specific.
Here are some sample sound waves:
These images show sound wave samples obtained from two different people saying 'yes'. Already, one can identify the characteristics of the different phones. The beginning of each sound (wherein the 'y' is spoken) is characterized by a quite regular sound wave, while the middle section (wherein the 'e' is spoken) appears to contain a combination of multiple frequencies. The trailing section (wherein the 's' is spoken) is in fact quite distinctive, characterized by a very high frequency, low energy sound wave. This distinctiveness is what motivated the decision to use the 's' as a reliable factor differentiating 'yes' from 'no'. Here is another sample showing the sound wave obtained from a speaker saying 'no'
Notice here that the 'n' is characterized by a single frequency, while the 'o' is a combination of frequencies. Another interesting feature is the presence of a small burst at the end of the sound. This may indicate the speaker punctuated the end of the 'o' with a quick 'w'. This is a simple case but it is complicated for bigger phonemes.
Speech Detection
The first task is to identify the presence of a speech signal. This task is easy if the signal is clear, however frequently the signal contains background noise. The signals obtained were in fact found to contain some noise. Two criterions are used to identify the presence of a spoken word. First, the total energy is measured, and second the number of zero crossings are counted. Both of these were found to be necessary, as voiced sounds tend to have a high total energy, but a low frequency, while unvoiced sounds were found to have a high frequency. Only background noise was found to have both low energy and low frequency. The method was found to successfully detect the beginning and end of the several words tested. Note that this is not sufficient for the general case, as fluent speech tends to have pauses, even in the middle of words (such as in the word 'acquire', between the 'c' and 'q'). In fact reliable speech detection is a difficult problem, and is an important part of speech recognition.
Blocking
The second task is blocking. Older speech recognition systems first attempted to detect where
the phones would start and finish, and then block the signal by placing one phone in each block. However, phones can blend together in many circumstances, and this method generally could not reliably detect the correct boundaries. Most modern systems simply separate the signal into blocks of a fixed length. These blocks tend to overlap, so that phones which cross block boundaries will not be missed. Here is what a typical block might
Block2:A block containing the 'EH' phone Block3: A block containing the 'S' phone
The difference between voiced and unvoiced sounds becomes clear in these samples. The first two blocks demonstrate a dominant low frequency sound wave, which is not present in the third block. This frequency is produced by the vibration of the larynx, or voice box. Although the exact frequency differs for each speaker (females tend to have a higher frequency), the dominant presence of a low frequency sound wave is a surefire indicator of a voiced sound.
Essentially all speech recognition systems use the same basic three-stage architecture:
• Feature detection in which the raw acoustic waveform is represented in a more useful space, typically a low-dimensional feature space based on coarse spectral measurements over a 10-50ms time window.
• Probabilistic classification of the feature vectors, in which the frames are scored as looking more or less likely as versions of a number of predefined sub word linguistic units.
• Search for best word-sequence hypothesis in which a word sequence is found that is consistent with the constraints of lexicon and grammar, and which corresponds to sub word unit sequence that is highly-ranked in the classifier output.
The Usefulness of Speech Recognition
Speech recognition is useful as a parsing tool:
It can allow us to easily search and index recorded audio and video data. Speech recognition is also useful as a form of input. It can allow people working in active environment such as hospitals to use computers. It can also allow people with handicaps to use computers. Finally, although everyone knows how to talk, not as many people know how to type. With speech recognition, typing would no longer be a necessary skill for using a computer. Many science fiction movies and books assume that combination, and give interesting examples of how it might change computing for the masses.
But even without natural language understanding, speech input changes the structure interfaces. For example, some telephone companies currently use speech input instead of number-pad menus. While speech input is good for dictation and choosing menu items, it may be harder to use as a navigation tool.
Conclusion
There are many factors involved in speech recognition. Although speech recognition technology seems relatively new, computer scientists have been continually developing it for the past 40 years. They’ve made great strides in improving the systems and processes, but the futuristic idea of your computer hearing and understanding you is still a long way off. However, there are numerous on-going projects that deal with topics such as the following:
• Visual cues to help computers decipher speech sounds that are obscured by environmental noise
• Speech-to-speech translation project for spontaneous speech
• Multi-engine Spanish-to-English machine translation system
• Building synthetic voices
REFERENCE • Encyclopedia of Science(King Fisher) • Time Life’s Illustrated World of Science • Britannica Encyclopedia ’99 Edition
BIBLIOGRAPHY • http://www.yahoo.com • http://www.google.com • http://www.altavista.com • http://www.wikipedia.com • http://www.speechrecognition.com
This paper deals with the topic SPEECH RECOGNITION which can make a revolution in the years to come. Speech recognition acts as an interface between the user and the system. Its applications vary to the extent that it is a successful replacement for input devices like Keyboard ,mouse etc. This paper contains information about Automatic Speech Recognition which decodes speech signals to phones, which is the basic building block of any word. Speech Recognition Systems are classified as Dependent and Independent Systems. Dependent systems recognize the sound generated by a single speaker whereas an Independent System recognizes sounds generated by multiple speakers. Based on the delivery of speech it is divided into two parts i.e. Isolated Word Systems and Continuous Speech Systems. An isolated-word system operates on single words at a time - requiring a pause between saying each word and a Continuous Speech System operates on speech in which words are connected together. There are several approaches to automatic speech recognition Acoustic-Phonetic, Artificial Intelligence and Pattern Recognition.
In this paper an experiment has been described, where the speech signal is converted into phonetics. These phones are combined together to form the word which is closest to the word spoken by the speaker and hence the recognition of the signal is successful. Graphs of few phones are shown in order to distinguish voiced and unvoiced sounds.
Speech recognition finds its major applications in the field of communication, access security, spontaneous data entry and artificial intelligence.
In the conclusion, the Speech Recognition systems has failed to give accurate result as the accent varies from one person to the other and also the other factors like environmental noise which makes significant contribution for the failure of such systems.
SPEECH RECOGNITION:
Introduction
Speech recognition technologies allow computers equipped with a source of sound input, such as a microphone, to interpret human speech, e.g., for transcription or as an alternative method of interacting with a computer Automatic Speech Recognition. Automatic speech recognition is the process by which a computer maps an acoustic speech signal to text. Automatic speech understanding is the process by which a computer maps an acoustic speech signal to some form of abstract meaning of the speech.
What does speaker dependent / adaptive / independent mean? A speaker dependent system is developed to operate for a single speaker. These systems are usually easier to develop, cheaper to buy and more accurate, but not as flexible as speaker adaptive or speaker independent systems.
A speaker independent system is developed to operate for any speaker of a particular type (e.g. American English). These systems are the most difficult to develop, most expensive and accuracy is lower than speaker dependent systems. However, they are more flexible.
A speaker adaptive system is developed to adapt its operation to the characteristics of new speakers. It's difficulty lies somewhere between speaker independent and speaker dependent systems.
What does small/medium/large/very-large vocabulary mean?
The size of vocabulary of a speech recognition system affects the complexity, processing requirements and the accuracy of the system. Some applications only require a few words (e.g. numbers only), others require very large dictionaries (e.g. dictation machines). There are no established definitions, however, try
• Small Vocabulary - tens of words
• Medium Vocabulary - hundreds of words
• Large Vocabulary - thousands of words
• Very-Large Vocabulary - tens of thousands of words.
• Medium Vocabulary - hundreds of words
• Large Vocabulary - thousands of words
• Very-Large Vocabulary - tens of thousands of words.
What does continuous speech and isolated-word mean? An isolated-word system operates on single words at a time - requiring a pause between saying each word. This is the simplest form of recognition to perform because the end points are easier to find and the pronunciation of a word tends not affect others. Thus, because the occurrences of words are more consistent they are easier to recognize.
A continuous speech system operates on speech in which words are connected together, i.e. not separated by pauses. Continuous speech is more difficult to handle because of a variety of effects. First, it is difficult to find the start and end points of words. Another problem is "co articulation". The production of each phoneme is affected by the production of surrounding phonemes, and similarly the start and end of words are affected by the preceding and following words. The recognition of continuous speech is also affected by the rate of speech (fast speech tends to be harder).
The Process of Speech Recognition There are several approaches to automatic speech recognition:
• Acoustic-Phonetic -- This approach is based on the idea that all spoken words can be split up into a finite group of phonetic units. If all of these phonetic units can be characterized computationally, one should be able to figure out what phonetic units have been spoken, and then decode them into words.
• Pattern Recognition -- This approach uses a training algorithm to teach a recognizer about the patterns present in specific words. It is similar to the acoustic-phonetic approach, but rather than defining the patterns explicitly (as phonetic units), Hidden Markov Model(HMM) based pattern recognizer finds it's own set of patterns.
• Artificial Intelligence -- This approach mixes the previous two approaches by combining phonetic, syntactic, lexical, and/or semantic based analysis with pattern recognition.
The Basic Steps:
The process of voice recognition is typically divided into several well defined steps. Different systems vary on the nature of these steps, as well as how each step is implemented, but the most successful systems follow a similar methodology.
• Divide the sound wave into evenly spaced blocks
• Process each block for important characteristics, such as strength across various frequency ranges, number of zero crossings, and total energy.
• Using these characteristics, attempt to associate each block with a Phone, which is the most basic unit of speech, producing a string of phones.
• Find the word whose model is the most likely match to the string of phones which was produced.
The Experiment:
Numerous samples were take of various people saying either 'yes' or 'no'. This method is somewhat artificial in that a real system first has to detect whether speech exists at all (this problem is the separate task of speech detection). Therefore we implemented a criteria for the detection of speech. The method is also somewhat artificial, because in fluent speech, words tend to run together and the word boundaries are not specific.
Here are some sample sound waves:
These images show sound wave samples obtained from two different people saying 'yes'. Already, one can identify the characteristics of the different phones. The beginning of each sound (wherein the 'y' is spoken) is characterized by a quite regular sound wave, while the middle section (wherein the 'e' is spoken) appears to contain a combination of multiple frequencies. The trailing section (wherein the 's' is spoken) is in fact quite distinctive, characterized by a very high frequency, low energy sound wave. This distinctiveness is what motivated the decision to use the 's' as a reliable factor differentiating 'yes' from 'no'. Here is another sample showing the sound wave obtained from a speaker saying 'no'
Notice here that the 'n' is characterized by a single frequency, while the 'o' is a combination of frequencies. Another interesting feature is the presence of a small burst at the end of the sound. This may indicate the speaker punctuated the end of the 'o' with a quick 'w'. This is a simple case but it is complicated for bigger phonemes.
Speech Detection
The first task is to identify the presence of a speech signal. This task is easy if the signal is clear, however frequently the signal contains background noise. The signals obtained were in fact found to contain some noise. Two criterions are used to identify the presence of a spoken word. First, the total energy is measured, and second the number of zero crossings are counted. Both of these were found to be necessary, as voiced sounds tend to have a high total energy, but a low frequency, while unvoiced sounds were found to have a high frequency. Only background noise was found to have both low energy and low frequency. The method was found to successfully detect the beginning and end of the several words tested. Note that this is not sufficient for the general case, as fluent speech tends to have pauses, even in the middle of words (such as in the word 'acquire', between the 'c' and 'q'). In fact reliable speech detection is a difficult problem, and is an important part of speech recognition.
Blocking
The second task is blocking. Older speech recognition systems first attempted to detect where
the phones would start and finish, and then block the signal by placing one phone in each block. However, phones can blend together in many circumstances, and this method generally could not reliably detect the correct boundaries. Most modern systems simply separate the signal into blocks of a fixed length. These blocks tend to overlap, so that phones which cross block boundaries will not be missed. Here is what a typical block might
Block2:A block containing the 'EH' phone Block3: A block containing the 'S' phone
The difference between voiced and unvoiced sounds becomes clear in these samples. The first two blocks demonstrate a dominant low frequency sound wave, which is not present in the third block. This frequency is produced by the vibration of the larynx, or voice box. Although the exact frequency differs for each speaker (females tend to have a higher frequency), the dominant presence of a low frequency sound wave is a surefire indicator of a voiced sound.
Essentially all speech recognition systems use the same basic three-stage architecture:
• Feature detection in which the raw acoustic waveform is represented in a more useful space, typically a low-dimensional feature space based on coarse spectral measurements over a 10-50ms time window.
• Probabilistic classification of the feature vectors, in which the frames are scored as looking more or less likely as versions of a number of predefined sub word linguistic units.
• Search for best word-sequence hypothesis in which a word sequence is found that is consistent with the constraints of lexicon and grammar, and which corresponds to sub word unit sequence that is highly-ranked in the classifier output.
The Usefulness of Speech Recognition
Speech recognition is useful as a parsing tool:
It can allow us to easily search and index recorded audio and video data. Speech recognition is also useful as a form of input. It can allow people working in active environment such as hospitals to use computers. It can also allow people with handicaps to use computers. Finally, although everyone knows how to talk, not as many people know how to type. With speech recognition, typing would no longer be a necessary skill for using a computer. Many science fiction movies and books assume that combination, and give interesting examples of how it might change computing for the masses.
But even without natural language understanding, speech input changes the structure interfaces. For example, some telephone companies currently use speech input instead of number-pad menus. While speech input is good for dictation and choosing menu items, it may be harder to use as a navigation tool.
Conclusion
There are many factors involved in speech recognition. Although speech recognition technology seems relatively new, computer scientists have been continually developing it for the past 40 years. They’ve made great strides in improving the systems and processes, but the futuristic idea of your computer hearing and understanding you is still a long way off. However, there are numerous on-going projects that deal with topics such as the following:
• Visual cues to help computers decipher speech sounds that are obscured by environmental noise
• Speech-to-speech translation project for spontaneous speech
• Multi-engine Spanish-to-English machine translation system
• Building synthetic voices
REFERENCE • Encyclopedia of Science(King Fisher) • Time Life’s Illustrated World of Science • Britannica Encyclopedia ’99 Edition
BIBLIOGRAPHY • http://www.yahoo.com • http://www.google.com • http://www.altavista.com • http://www.wikipedia.com • http://www.speechrecognition.com