Saturday, June 18, 2016

audium

I recently heard about a theater in California with approximately 170 speakers ranging from low quality tweeters to more expensive ones. While performances in the dark took place these speakers moved around. They were programmed electronically. This is interesting when tied to this research because it is an interesting study about context ot lack of context. It is physically impossible to see what generated the sound. Yet based on placement we may be able to assume things. It brings back memories of what produced the sound in the past. It also helps us evaluate his well we learn things. When making assertion we rule out the least logical and the more solid assertions remain. Psychologists do a test where they do not explain the rules yet they guide participants towards a an objective through saying if the action was correct or incorrect. This is what my the purpose of what is done by eliminating what is not the topic as shown by the computer attempting to solve the where's Waldo puzzle.

I hope to work more on this project with reading the following books:

the master algorithm

the ghost inside my head

how to think about machines that think


Thursday, September 24, 2015

sound nodes surrounded by overwhelming clues

Change blindness as described in the book Invisible Gorilla, talks about how we long for continuity. However, in this blog post I argue that this pattern matching classification is done to overlook elements in sound. Naturally we each have a certain range of activities that go unnoticed. Sometimes this varies from person to person, a common example being tinnitus. Like light, sound is often measured in how it is different from one element to the next such as pitch. Sound appears unified until broken apart by a prism called a spectrometer. This helps us figure out what the light emitting object is constructed and composed. We are unable to tell boundaries is two fold. First the mind likes unifying patterns into things it can understand and find patterns between two "corresponding" events. This is so we can communicate what it is we saw. This is despite the entrophy and separations posed by natural limitations such as quantum mechanics in harmonic wave functions The second reason is pink noise also known as Brownian motion or noise that we disregard as background noise. This is what audiologists call masking and can dampens boundaries between two events in sound. However, I am uncertain that most pink noise is extraneous. It could provide useful clues as to the context of the speech. By harmonic analysis and studying representational theory. This can be explored in the study of continuous-time Markov chain. This uses the analogy of how elements combined in a certain way makes a chemical reaction. Grammar is different and cannot be measured by finite states but rather provide a framework of rules for processing. Rather it can be seen as a horde of ants interacting and otherwise affecting their evolutionary walks. Naomi Chomsky talked about how rules do not necessarily guarantee a sentence. For example the notion that "Green colorless ideas sleep furiously" is a sentence is simply unsound. David Ben-Zvi uses a concept he describes as the x-games to describe infinitesimal generator matrix. By using differentials to study the elements in an evolution of sounds. In my papers I've discussed the benefits of starting to play musical instruments as a younger person (some would argue ideally preschool aged). This is because it raises the awareness and attention of the threshold between two different events musically.

To summarize: the blackboard algorithm combined with a neural network is a good approach to the complexity of sound. In order to fully appreciate the significance of each node, we not only need what is preceding it but what is going on simultaneously that provide clues as to what might happen in the future. In my paper I suggest that one reason why people have difficulty speaking is that their mind is not able to function and keep up with everything. In this area I believe computers can excel because as computers become more powerful, they can surpass human's attention spans.

The ants marching in a row is a nice picture but seldom happens because of the simultaneous complex world we live in.

I am reading more math books in order to be able to grasp the differential equations that are needed to study the flow of words.

I am confident that with the emerging field of multi-processor concurrency and abandoning the idea of having a master core and adopting a system more like the brain of adopting many neurons firing electrical signals would bear success in the years to come. There is a consensus and each core is aware of what is going on.

Wednesday, June 3, 2015

The Frame of Mind and Balance between Extremes

During the Google IO 2015, Google announced that they have a body of work suggesting that sentiment analysis can annotate a state of mind. I appriciate the research that Google makes and how they make some of their papers available online at http://research.google.com . I've listened to the TED "Using Twitter to Predict Heart Disease" using sentiment analysis can predict healthy hearts by the number of positive statements at https://youtu.be/FjibavNwOUI . While we appriciate Lyle Ungar
 having spent the time to map out most common elements in conversations in many conversations, there are some psychological an statistical features that demand a verdict. For example, how do we map the line between micro and macro society. In today's world we are more interconnected than ever through such mechanisms such as Facebook. There have been studies on Facebook saying that people emphesize the positive and the negative is not discussed as often. However if someone had a negative experience they often turn it into a joke. Commedians have in their arsenol of jokes a series of possible awkward moments. Also a negative comment is more likely to be remembered as opposed to a negative statement. For instance the news is coverage of fires in people's homes and they tend to talk about how many homes were burned in a wildfire as opposed to how many people houses were saved. While a house burned by a wildfire is indeed a tragic event, not as many people discuss the tremental amount of damage caused by wood eating insects. This is deemed to be an embarrasment. So what draws the line between one time sudden tragic events and slowly over time tragic events. A myth is that the pest problem is easy to deal with and reflects poorly on the owners of the facilities destroyed. However, once when talking to termite companies they cite such methods as putting stakes about 6 inches long into the ground and hoping that the termites eat this wood so they can tell whether or not there are termites. This is laughable because of all the dead roots of current and former trees in the area. Another vendor said they recommend building a moat of posion around our house and fumagating the house. This is as uneffective as it is unpractical.

The third objection that I have to determine sentiment analysis is the apparent lack of response from authority and therefore we assume that no one is in charge. Economics is defined as the distribution of goods when there is an uneven or unreliable source of these goods. Since there is always people who want or need more than they have, there would be conflicts. Lyle Ungar has a good point in his Ted Talk when he says that people are more happy when they have an opportunity to give to a friend than get something for themselves, should they get awarded the money, perhaps in TV show. There is a statistic that people who win awards are often more poor because they are approached by people who they care about who have needs that they empathize with. In instances like these where the person is so hounded with the needs of others, they often feel burned out. This brings an interesting point of people's desire to be recognized for their acts of kindness and not having an administration that puts weight where it can be beared. We all have experiences when we build a precident of being nice when people in order to survive depend on this act of kindness to be recurrent and perhaps increase. I've read a book which suggested that people who have a skill such as graphic design work or web design work should not volunteer their work but rather exchange the work for something of value. They cited the reason of cheapening the profession and even making it harder for people who do the work for a living to do so because once a precident is built of someone doing the work for free, the work is seen as something that should be done forever. Sometimes parents sit by their sick baby and wish there was something they can do. They sometimes wonder if there is some way to take the place of the baby. They do not have soverienty over disease, however great they are willing to sacrifice.

For those who read scripture might recognize the difficulty of recognizing sentiment in such passages as the 89th Psalm. The psalm is of an unknown person who is said to be a brilliant contemporary of Solomon. It reads:

Psalm 89 GOD’S WORD Translation (GW)

I will sing forever about the evidence of your mercy, O Lord.
I will tell about your faithfulness to every generation.
I said, “Your mercy will last forever.
    Your faithfulness stands firm in the heavens.”
You said, “I have made a promise[a] to my chosen one.
    I swore this oath to my servant David:
        ‘I will make your dynasty continue forever.
        I built your throne to last throughout every generation.’” Selah
O Lord, the heavens praise your miracles
    and your faithfulness in the assembly of the holy ones.
Who in the skies can compare with the Lord?
Who among the heavenly beings is like the Lord?
God is terrifying in the council of the holy ones.
He is greater and more awe-inspiring than those who surround him.
O Lord God of Armies, who is like you?
Mighty Lord, even your faithfulness surrounds you.
    You rule the raging sea.
        When its waves rise, you quiet them.
10     You crushed Rahab;[b] it was like a corpse.
    With your strong arm you scattered your enemies.
11 The heavens are yours.
The earth is also yours.
You made the world and everything in it.
12     You created north and south.
        Mount Tabor and Mount Hermon sing your name joyfully.
13     Your arm is mighty.
    Your hand is strong.
    Your right hand is lifted high.
14 Righteousness and justice are the foundations of your throne.
Mercy and truth stand in front of you.
15 Blessed are the people who know how to praise you.
    They walk in the light of your presence, O Lord.
16     They find joy in your name all day long.
    They are joyful in your righteousness
17         because you are the glory of their strength.
By your favor you give us victory.[c]
18 Our shield belongs to the Lord.
Our king belongs to the Holy One of Israel.
19 Once in a vision you said to your faithful ones:
    “I set a boy above warriors.[d]
    I have raised up one chosen from the people.
20     I found my servant David.
    I anointed him with my holy oil.
21         My hand is ready to help him.
        My arm will also give him strength.
22             No enemy will take him by surprise.
            No wicked person will mistreat him.
23     I will crush his enemies in front of him
        and defeat those who hate him.
24     My faithfulness and mercy will be with him,
        and in my name he will be victorious.[e]
25     I will put his left hand on the sea
        and his right hand on the rivers.
26     He will call out to me,
        ‘You are my Father, my God, and the rock of my salvation.’
27     Yes, I will make him the firstborn.
        He will be the Most High to the kings of the earth.
28     My mercy will stay with him forever.
    My promise to him is unbreakable.
29     I will make his dynasty endure forever
        and his throne like the days of heaven.
30     “If his descendants abandon my teachings
        and do not live by my rules,
31     if they violate my laws
        and do not obey my commandments,
32     then with a rod I will punish their rebellion
        and their crimes with beatings.
33     But I will not take my mercy away from him
        or allow my truth to become a lie.
34     I will not dishonor my promise
        or alter my own agreement.
35     On my holiness I have taken an oath once and for all:
        I will not lie to David.
36         His dynasty will last forever.
        His throne will be in my presence like the sun.
37             Like the moon his throne will stand firm forever.
                It will be like a faithful witness in heaven.”
38 But you have despised, rejected,
    and become angry with your anointed one.
39 You have refused to recognize the promise to your servant
    and have thrown his crown into the dirt.
40 You have broken through all his walls
    and have laid his fortified cities in ruins.
41         (Everyone who passed by robbed him.
            He has become the object of his neighbors’ scorn.)
42 You held the right hand of his enemies high
    and made all of his adversaries rejoice.
43 You even took his sword out of his hand
    and failed to support him in battle.
44 You put an end to his splendor
    and hurled his throne to the ground.
45 You cut short the days of his youth
    and covered him with shame. Selah
46 How long, O Lord? Will you hide yourself forever?
How long will your anger continue to burn like fire?
47 Remember how short my life is!
    Have you created Adam’s descendants for no reason?
48         Can a mortal go on living and never see death?
            Who can set himself free from the power of the grave? Selah
49                 Where is the evidence of your mercy, Lord?
                    You swore an oath to David
                        on the basis of your faithfulness.
50 Remember, O Lord,[f] how your servant[g] has been insulted.
Remember how I have carried in my heart the insults from so many people.
51     Your enemies insulted me.
        They insulted your Messiah[h] every step he took.
52                     Thank the Lord forever.
                                Amen and amen!

There are numerous signs of positive sentiment but also of negative sentiment. The point is that in order to understand sentiment, we must dive deeper into context. Clear audio aims to be a cross domain cross language software package. This can be done through analyzing what this text is not. For example, my paper refers to CAPTCHYAS and solving puzzels by remebering things that they are not. Another agent derives the business logic in UML explained by Jan Dietz with whose library example is recalled in my paper. What do all these things have in common? One talk I heard about this passage was labeled "Finding Assurance in Uncertain Times". One quote he says is some things once gleamed as certainty curls into a question mark. This is why a holistic perspective is needed to gleam what this passage means.

This points out that a person is not in control of our destinies any more than we are in control of external elements to a discussion. Often a discussion is a two way talk. Each person responds and makes suggestions to the other. Sometimes they might try to persuade the person to think differently and to think about the topic in a larger context. What if the cell phone on either end of the conversation were to loose power. That would change the trajectory tremendously. This swaying can be measured much like a person walks in accordance with an intersection of the the aims of the two people in a conversation. We should ask ourselves what is needed for each party to survive. Barring physical interference, most of the purpose of a conversation comes down to a human's gut insticts of survival. The movie a beautiful mind points out that there is a series of compromises when a person lives in a society. John Nash had a good insight into this matter when he commented on being different and having what he described as "thought police" come after him to get him to conform to the normals of society. In the pest compared to the fire situation above, the reason why a fire is given greater attention than a pest is because in the case of a fire, we rally around the people as they come to grasp with the fire and move on with their lives. I heard a person talk about one of the things airline steward says is something to the effect of "in case of an emergency first get the oxygen mask on yourself and then help your neighbor." Should a person attempt to switch the order, their work would be less efficient and therefore a less chance of survival. This forms an equalibrium described in detail in the book, The Plague by Albert Camus. The story tells of a village that is shut down by it's own actions. They are under the assumption that the end of the world is upon them, and make a number of steps to fulfill the prophacy. They underestimate the importance of rats in a population, which are not causing a problem, they are just not beatiful to look at. Then they inadvertantly cause the epidemic plague. They next shut themselves off from the outside world, thus causing a sortage of medical supplies and training on how other villages are dealing with the problem. The third thing they do that hurts them is that people begin lawness in the streets and looting because it they figure they do not have to live with the consequences of tomorrow, why not? The minister is a good man and has good ideas but since he does not have the support of the community, he overextends himself and is a casualty of the plague. Later when they realize that the plague is dying down because they start seeing life in perspective, they stop the measures that are depremental and have a new appriciation for a balance in life.

Points for discussion:
Equalibrium brought between sentiment (nothing is entirely negative or positive)
Context is essential
The deviance between the equalibrium and the origionating point can be measured

Wednesday, March 4, 2015

A paper I wrote is available at http://dx.doi.org/10.6084/m9.figshare.1275341

paper available at researchgate and academia.edu

I've discussed with people on researchgate about what causes speech problems and looked at some speech pathology lecture  notes. Then i rearranged my research around the question of what do we do if people are aware that they have speaking difficulties vs if they are not aware. heren is an excerpt of my new paper

There are two classes of people with speech challenges,
the first class consists of those who had trouble speaking
since birth. They are aware of the fact they are more
challenging to understand. One hypothesis on speaking
challenges is the disorder is more prevalent in children
because they are overwhelmed by the conceptualizing and
the formatting tasks of language. Bell Labs engineer Robert
Lucky estimated the cortex cannot take more than 50 bits
per second. Mihaly Csikszentmihalyi estimated one
apperception to take 1/15th of a second or 105 bits per
second. Regardless of the figure a person has limited
bandwidth or computing power. Because it takes a lot of
concentration to come up with metaphors and categorize
ideas with words, the quality of speech declines. Along
with this speech has limited prosody referred to in this
paper as words per minute, pitch variance, and stress of
syllables. With the knowledge that they can be
unintelligible, they compensate using repetition or choose
words that does not contain the element that they have
trouble with. They may do these substitutions or
repetitions unconsciously. People with speech aphasia
often have trouble with pronouns. A goal of Clear Audio is
to find the use of pronouns and the repetition by using
summarizing tools. These methods are discussed in section
2. Other people have difficulty speaking later in life due to
a stroke may be confident that their pronunciation is the
same as it was before their decline and may not
incorporate either repetition or choice of words. The
second case is discussed in section 3.

Sunday, August 3, 2014

word signatures including gestures

Words by themselves are very difficult for speech recognizers to work witb. Consider the phrase "eats, shoots, and leaves". There is a lot of ambiguity as far as what kind of leaves is this referring to. Does it mean to abandon or a part of a plant. Humans, even those who have "practiced" the art of being social for 10,000 hours or once a person turns 10 cannot be expected to know all there is about every idiom and ventricle metaphor since the beginning of time. Therefore something else is happening. The book "Mirroring people" poses the queston of why is it that a person gestures when they are talking on a phone and it is impossible for the other person to be able to see them. It is because we use words as a vehicle to transport the other person to a thought or feeling we wish to convey. Many nlp practitioners use stemming as a way to isolate meaning but this will not work because words without context is empty. We establish context with pitch, tempo, and liveliness. The book "Social Physics" asks us to imagine a device that isolates the spoken word from the manner in which it is spoken. For example pitch, tempo and liveliness. This will also fail to grasp the full meaning. For us to do that we need to think of a human brain and how it condenses meaning  so a person does not think too hard. The book "We are our brains" discusses one theory that a person uses the equivalent of $1500 for their entire life or 15 watts per hour.  In order to come up with a computational model we need to ask the right questions. What some large speech recognition platforms is doing by training their system by using 30,000 people voices speaking. This is wrong because we need to think of words and concepts as being unique. By over complexity we slow down the system so it is not usable in real time and requires vast amounts of computing power beyond what is in our phones. Some systems make this a crowdsourcing problem and remove the computing resources into the cloud. Computer security specialists know the problem with this approach is that while some conversations glob together some certaintly do not. This is not a matter of a big enough sample, there is nothing we can do. The book "Uncharted"explains how almost in a decade worth of Google searches some queries stand out. What my clear audio project proposes to do is tot build a blackboard like system based off how we understand the human mind to work. To do this we need to extend an artificial neural network. An artificial neural network is a single parameter engine that comes up with a single parameter result baed on recursion and removing the strands that are not used very much. While we do have need for a single parameter output we do not yet have a nicely formatted single parameter vector of input. We need a blackboard system with several parameters from multiple agents.  We can use what we learned from visual saliency to find feature sets. For example consider the book wher's waldo. First a featuee that we may associate with waldo is that he wears red. Then we look for stripes. Then we look for glasses. Then for certian we know where waldo is. This process is not unlike what we do with with clear audio. We take a vector of certainties and study the senttence trajectory. Using ziff's law we know how a topic is formed and diverged from. We know that every conversation has a topic sentence. It is unusual for a person to call another without a particular question in mind, even if it is to see how their day went. That conversation has a subect of the day.  We need to ask the contexual questions formed by Zachman's formula: what, when, who, how, and why. By studying a person's speech including pitch, tempo, and liveliness as well as the words they actually do say, future words can be predicted. By living in the experience we can allow our nlp engines to detect starcasm.

Wednesday, July 9, 2014

tone tempo viverance

The aspects of my research that set it apart from other speech recognizing software is that they attempt to match phonemes with phonetic words. My approach builds on this but uses a blackboard approach. A  blackboard has multiple agents that evaluate an aspect and throws throws it into a processing system. In this approach the words are a feature and so are tone (pitch) tempo and viverance. This is important because like my paper Jurassic Park Extrapolation Renders Speech to Speech engine greater accuracy mentions the brain is constantly bombarded with signals and information. The brain has trained itself to ignore some sounds such as the 60 hertz drone of a light bulb fixture. The brain needs some difference and variance in order to stay focused. When a robotic voice speaks it is often draining to listen to. I hope to find a feature set to annotate and make computers easier to listen to. I am currently working on looking at integrating the Neuromorphic Vision C++ Toolkit with gbbopen and pybrain. I hope to be able to understand the algorithms well enough to port them all to python and so it can run on an android. GBBOpen is written in lisp and neuromorphic Vision C++ Toolkit is written in C++.