HTK (Hidden Markov Model Toolkit) is a proprietary software toolkit for handling HMMs. It is mainly intended for speech recognition, but has been used in many other pattern recognition applications that employ HMMs, including speech synthesis, character recognition and DNA sequencing. Originally developed at the Machine Intelligence Laboratory (formerly known as the Speech Vision and Robotics Group) of the Cambridge University Engineering Department (CUED), HTK is now being widely used among researchers who are working on HMMs.
Agent-assisted automation
Agent-assisted automation is a type of call center technology that automates elements of what the call center agent 1) does with his/her desktop tools and/or 2) says to customers during the call using pre-recorded audio. It is a relatively new category of call center technology that shows promise in improving call center productivity and compliance. == Types of agent-assisted automation == === Pre-recorded audio === Pre-recorded audio (sometimes referred to as soundboard (computer program) or as soundboard technology) is another form of agent-assisted automation. The purpose of using pre-recorded messages is to increase the probability (and in some cases error-proof the process so) that the right information is provided to customers at the right time. The required disclosures are pre-recorded to ensure accuracy and understandability. By integrating the recordings with the customer relationship management software, the right combination of disclosures can be played based on the combination of goods and services the customer purchased. The integration with the customer relationship management software also ensures that the order cannot be submitted until the disclosures are played, essentially error-proofing (poka-yoke) the process of ensuring the customer gets all the required consumer protection information. Phone surveys are ideal applications of this technology. Whether surveying market preferences or political views, the pre-recorded audio with an agent listening allows the questions to be asked in the same way every time, uninfluenced by the agents' fatigue levels, accents, or their own views. === Fraud prevention === Fraud prevention is a specialized type of agent-assisted automation focused on reducing ID theft and credit card fraud. ID theft and credit card fraud are huge threats for call centers and their customers and few good solutions exist, but new agent-assisted automation solutions are producing promising results. The technology allows the agents to remain on the phone while the customers use their phone key pads to enter the information. The tones are masked and the information passes directly into the customer relationship management system or payment gateway in the case of credit card transactions. The automation essentially makes it impossible for call center agents and also call center personnel that might be monitoring the calls to steal the credit card number, social security number, or other personally identifiable information. === Outbound telemarketing === Another specialized application space of agent-assisted automation is in outbound telemarketing, which goes under numerous headings including outbound prospecting, cold calling, solicitation, fund-raising, etc. Turnover is high among agents engaged in this kind of work because the task is tedious and emotionally difficult. It is tedious because the agent spends the bulk of their day, not talking to qualified leads, but in getting wrong numbers and answering machines. == Benefits == Just as automation has benefited manufacturing by reducing the mental and physical effort required of workers while simultaneously improving throughput, quality, and safety, agent-assisted automation is improving call center results while reducing the tiring aspects of the job for agents. In some cases, the agent-assisted automation streamlines the process and allows calls to be handled more quickly. By eliminating cutting and pasting from one application to another, by auto-navigating applications, and by providing a single view of the customer, agent-assisted automation can reduce call handle time and increase agent productivity. Second, in theory, the more steps that can be automated and the more logic that can be built into the call flow (e.g., if the customer buys items 2 and 9, then disclosures a, c, and f are read by the pre-recorded audio), then companies may be able to reduce the amount of training that is required of the agents while at the same time ensuring more consistency and accuracy. However, no published studies have reported this result yet. But an even larger problem in call centers is between-agent variation in behavior and results. Agents differ in the amount of training and coaching they receive, they differ in the amount of experience they have, their jobs are repetitious and tiring, and the process and procedures the agents are supposed to follow constantly change. Moreover, there are significant individual differences between agents in their intelligence, personality, motivations, etc. which all affect performance. Despite the large amount of money call centers have spent over decades trying to reduce between-agent variation, the problem is still so prevalent that one large study of customer interactions with call centers found that a customer's experience was completely a function of the quality of the agent who happened to answer the phone. Therefore, the most significant benefit of agent-assisted automation may prove to be in how the automation error-proofs or poka-yoke the process and ensures that something that needs to be done or said happens every time. Properly implemented, the between-agent variation for whatever step of the process the automation is applied to may be able to be reduced to near zero. This is especially important in a collection agency whose processes and procedures are closely regulated by the Fair Debt Collection Practices Act.
Supersampling
Supersampling or supersampling anti-aliasing (SSAA) is a spatial anti-aliasing method, i.e. a method used to remove aliasing (jagged and pixelated edges, colloquially known as "jaggies") from images rendered in computer games or other computer programs that generate imagery. Aliasing occurs because unlike real-world objects, which have continuous smooth curves and lines, a computer screen shows the viewer a large number of small squares. These pixels all have the same size, and each one has a single color. A line can only be shown as a collection of pixels, and therefore appears jagged unless it is perfectly horizontal or vertical. The aim of supersampling is to reduce this effect. Color samples are taken at several instances inside the pixel (not just at the center as normal)—hence the term "supersampling"—and an average color value is calculated. This can for example be achieved by rendering the image at a much higher resolution than the one being displayed, then shrinking it to the desired size, using the extra pixels for calculation, with the result being a downsampled image with smoother transitions from one line of pixels to another along the edges of objects, but each pixel could also be supersampled using other strategies (see the Supersampling patterns section). The number of samples determines the quality of the output. == Motivation == Aliasing is manifested in the case of 2D images as moiré pattern and pixelated edges, colloquially known as "jaggies". Common signal processing and image processing knowledge suggests that to achieve perfect elimination of aliasing, proper spatial sampling at the Nyquist rate (or higher) after applying a 2D Anti-aliasing filter is required. As this approach would require a forward and inverse fourier transformation, computationally less demanding approximations like supersampling were developed to avoid domain switches by staying in the spatial domain ("image domain"). == Method == === Computational cost and adaptive supersampling === Supersampling is computationally expensive because it requires much greater video card memory and memory bandwidth, since the amount of buffer used is several times larger. A way around this problem is to use a technique known as adaptive supersampling, where only pixels at the edges of objects are supersampled. Initially only a few samples are taken within each pixel. If these values are very similar, only these samples are used to determine the color. If not, more are used. The result of this method is that a higher number of samples are calculated only where necessary, thus improving performance. === Supersampling patterns === When taking samples within a pixel, the sample positions have to be determined in some way. Although the number of ways in which this can be done is infinite, there are a few ways which are commonly used. ==== Grid ==== The simplest algorithm. The pixel is split into several sub-pixels, and a sample is taken from the center of each. It is fast and easy to implement. Although, due to the regular nature of sampling, aliasing can still occur if a low number of sub-pixels is used. ==== Random ==== Also known as stochastic sampling, it avoids the regularity of grid supersampling. However, due to the irregularity of the pattern, samples end up being unnecessary in some areas of the pixel and lacking in others. ==== Poisson disk ==== The Poisson disk sampling algorithm places the samples randomly, but then checks that any two are not too close. The end result is an even but random distribution of samples. The naive "dart throwing" algorithm is extremely slow for large data sets, which once limited its applications for real-time rendering. However, many fast algorithms now exist to generate Poisson disk noise, even those with variable density. The Delone set provides a mathematical description of such sampling. ==== Jittered ==== A modification of the grid algorithm to approximate the Poisson disk. A pixel is split into several sub-pixels, but a sample is not taken from the center of each, but from a random point within the sub-pixel. Congregation can still occur, but to a lesser degree. ==== Rotated grid ==== A 2×2 grid layout is used but the sample pattern is rotated to avoid samples aligning on the horizontal or vertical axis, greatly improving antialiasing quality for the most commonly encountered cases. For an optimal pattern, the rotation angle is arctan (1/2) (about 26.6°) and the square is stretched by a factor of √5/2, making it also a 4-queens solution.
Luma (video)
In video, luma ( Y ′ {\displaystyle Y'} ) represents the brightness in an image (the "black-and-white" or achromatic portion of the image). Luma is typically paired with chroma. Luma represents the achromatic image, while the chroma components represent the color information. Converting R′G′B′ sources (such as the output of a three-CCD camera) into luma and chroma allows for chroma subsampling: because human vision has finer spatial sensitivity to luminance ("black and white") differences than chromatic differences, video systems can store and transmit chromatic information at lower resolution, optimizing perceived detail at a particular bandwidth. == Luma versus relative luminance == Luma is the weighted sum of gamma-compressed R′G′B′ components of a color video—the prime symbols ′ denote gamma compression. The word was proposed to prevent confusion between luma as implemented in video engineering and relative luminance as used in color science (i.e. as defined by CIE). Relative luminance is formed as a weighted sum of linear RGB components, not gamma-compressed ones. Even so, luma is sometimes erroneously called luminance. SMPTE EG 28 recommends the symbol Y ′ {\displaystyle Y'} to denote luma and the symbol Y {\displaystyle Y} to denote relative luminance. === Use of relative luminance === While luma is more often encountered, relative luminance is sometimes used in video engineering when referring to the brightness of a monitor. The formula used to calculate relative luminance uses coefficients based on the CIE color matching functions and the relevant standard chromaticities of red, green, and blue (e.g., the original NTSC primaries, SMPTE C, or Rec. 709). For the Rec. 709 (and sRGB) primaries, the linear combination, based on pure colorimetric considerations and the definition of relative luminance is: Y = 0.2126 R + 0.7152 G + 0.0722 B {\displaystyle Y=0.2126R+0.7152G+0.0722B} The formula used to calculate luma in the Rec. 709 spec arbitrarily also uses these same coefficients, but with gamma-compressed components: Y ′ = 0.2126 R ′ + 0.7152 G ′ + 0.0722 B ′ , {\displaystyle Y'=0.2126R'+0.7152G'+0.0722B',} where the prime symbol ′ denotes gamma compression. == Rec. 601 luma versus Rec. 709 luma coefficients == For digital formats following CCIR 601 (i.e. most digital standard definition formats), luma is calculated with this formula: Y 601 ′ = 0.299 R ′ + 0.587 G ′ + 0.114 B ′ {\displaystyle Y'_{\text{601}}=0.299R'+0.587G'+0.114B'} Formats following ITU-R Recommendation BT. 709 (i.e. most digital high definition formats) use a different formula: Y 709 ′ = 0.2126 R ′ + 0.7152 G ′ + 0.0722 B ′ {\displaystyle Y'_{\text{709}}=0.2126R'+0.7152G'+0.0722B'} Modern HDTV systems use the 709 coefficients, while transitional 1035i HDTV (MUSE) formats may use the SMPTE 240M coefficients: Y 240 ′ = 0.212 R ′ + 0.701 G ′ + 0.087 B ′ = Y 145 ′ {\displaystyle Y'_{\text{240}}=0.212R'+0.701G'+0.087B'=Y'_{\text{145}}} These coefficients correspond to the SMPTE RP 145 primaries (also known as "SMPTE C") in use at the time the standard was created. The change in the luma coefficients is to provide the "theoretically correct" coefficients that reflect the corresponding standard chromaticities ('colors') of the primaries red, green, and blue. However, there is some controversy regarding this decision. The difference in luma coefficients requires that component signals must be converted between Rec. 601 and Rec. 709 to provide accurate colors. In consumer equipment, the matrix required to perform this conversion may be omitted (to reduce cost), resulting in inaccurate color. == Luma and luminance errors == As well, the Rec. 709 luma coefficients may not necessarily provide better performance. Because of the difference between luma and relative luminance, luma does not exactly represent the luminance in an image. As a result, errors in chroma can affect luminance. Luma alone does not perfectly represent luminance; accurate luminance requires both accurate luma and chroma. Hence, errors in chroma "bleed" into the luminance of an image. Note the bleeding in lightness near the borders. Due to the widespread usage of chroma subsampling, errors in chroma typically occur when it is lowered in resolution/bandwidth. This lowered bandwidth, coupled with high frequency chroma components, can cause visible errors in luminance. An example of a high frequency chroma component would be the line between the green and magenta bars of the SMPTE color bars test pattern. Error in luminance can be seen as a dark band that occurs in this area.
Speech recognition
Speech recognition (automatic speech recognition (ASR), computer speech recognition, or speech-to-text (STT)) is a sub-field of computational linguistics concerned with methods and technologies that translate spoken language into text or other interpretable forms. Speech recognition applications include voice user interfaces, where the user speaks to a device, which "listens" and processes the audio. Common voice applications include interpreting commands for calling, call routing, home automation, and aircraft control. These applications are called direct voice input. Productivity applications include searching audio recordings, creating transcripts, and dictation. Speech recognition can be used to analyse speaker characteristics, such as identifying native language using pronunciation assessment. Voice recognition (speaker identification) refers to identifying the speaker, rather than speech contents. Recognizing the speaker can simplify the task of translating speech in systems trained on a specific person's voice. It can also be used to authenticate the speaker as part of a security process. == History == Applications for speech recognition developed over many decades, with progress accelerated due to advances in deep learning and the use of big data. These advances are reflected in an increase in academic papers, and greater system adoption. Key areas of growth include vocabulary size, more accurate recognition for unfamiliar speakers (speaker independence), and faster processing speed. === Pre-1970 === 1952 – Bell Labs researchers, Stephen Balashek, R. Biddulph, and K. H. Davis, built Audrey for single-speaker digit recognition. Their system located the formants in the power spectrum of each utterance. 1960 – Gunnar Fant developed and published the source–filter model of speech production. 1962 – IBM's 16-word "Shoebox" machine's speech recognition debuted at the 1962 World's Fair. 1966 – Linear predictive coding, a speech coding method, was proposed by Fumitada Itakura of Nagoya University and Shuzo Saito of Nippon Telegraph and Telephone. 1969 – Funding at Bell Labs came to a halt for several years after the company's head engineer, John R. Pierce, wrote an open letter criticizing speech recognition research. This defunding lasted until Pierce retired and James L. Flanagan took over. Raj Reddy was the first person to work on continuous speech recognition, as a graduate student at Stanford University in the late 1960s. Previous systems required users to pause after each word. Reddy's system issued spoken commands for playing chess. Around this time, Soviet researchers invented the dynamic time warping (DTW) algorithm and used it to create a recognizer capable of operating on a 200-word vocabulary. DTW processed speech by dividing it into short frames (e.g. 10 ms segments) and treating each frame as a unit. Speaker independence, however, remained unsolved. === 1970–1990 === 1971 – DARPA funded a five-year speech recognition research project, Speech Understanding Research, seeking a minimum vocabulary size of 1,000 words. The project considered speech understanding a key to achieving progress in speech recognition, which was later disproved. BBN, IBM, Carnegie Mellon (CMU), and Stanford Research Institute participated. 1972 – The IEEE Acoustics, Speech, and Signal Processing group held a conference in Newton, Massachusetts. 1976 – The first ICASSP was held in Philadelphia, which became a major venue for publishing on speech recognition. During the late 1960s, Leonard Baum developed the mathematics of Markov chains at the Institute for Defense Analysis. A decade later, at CMU, Raj Reddy's students James Baker and Janet M. Baker began using the hidden Markov model (HMM) for speech recognition. James Baker had learned about HMMs while at the Institute for Defense Analysis. HMMs enabled researchers to combine sources of knowledge, such as acoustics, language, and syntax, in a unified probabilistic model. By the mid-1980s, Fred Jelinek's team at IBM created a voice-activated typewriter called Tangora, which could handle a 20,000-word vocabulary. Jelinek's statistical approach placed less emphasis on emulating human brain processes in favor of statistical modelling. (Jelinek's group independently discovered the application of HMMs to speech.) This was controversial among linguists since HMMs are too simplistic to account for many features of human languages. However, the HMM proved to be a highly useful way for modelling speech and replaced dynamic time warping as the dominant speech recognition algorithm in the 1980s. 1982 – Dragon Systems, founded by James and Janet M. Baker, was one of IBM's few competitors. === Practical speech recognition === The 1980s also saw the introduction of the n-gram language model. 1987 – The back-off model enabled language models to use multiple-length n-grams, and CSELT used HMM to recognize languages (in software and hardware, e.g. RIPAC). At the end of the DARPA program in 1976, the best computer available to researchers was the PDP-10 with 4 MB of RAM. It could take up to 100 minutes to decode 30 seconds of speech. Practical products included: 1984 – the Apricot Portable was released with up to 4096 words support, of which only 64 could be held in RAM at a time. 1987 – a recognizer from Kurzweil Applied Intelligence 1990 – Dragon Dictate, a consumer product released in 1990. AT&T deployed the Voice Recognition Call Processing service in 1992 to route telephone calls without a human operator. The technology was developed by Lawrence Rabiner and others at Bell Labs. By the early 1990s, the vocabulary of the typical commercial speech recognition system had exceeded the average human vocabulary. Reddy's former student, Xuedong Huang, developed the Sphinx-II system at CMU. Sphinx-II was the first to do speaker-independent, large vocabulary, continuous speech recognition, and it won DARPA's 1992 evaluation. Handling continuous speech with a large vocabulary was a major milestone. Huang later founded the speech recognition group at Microsoft in 1993. Reddy's student Kai-Fu Lee joined Apple, where, in 1992, he helped develop the Casper speech interface prototype. Lernout & Hauspie, a Belgium-based speech recognition company, acquired other companies, including Kurzweil Applied Intelligence in 1997 and Dragon Systems in 2000. L&H was used in Windows XP. L&H was an industry leader until an accounting scandal destroyed it in 2001. L&H speech technology was bought by ScanSoft, which became Nuance in 2005. Apple licensed Nuance software for its digital assistant Siri. ==== 2000s ==== In the 2000s, DARPA sponsored two speech recognition programs: Effective Affordable Reusable Speech-to-Text (EARS) in 2002, followed by Global Autonomous Language Exploitation (GALE) in 2005. Four teams participated in EARS: IBM; a team led by BBN with LIMSI and the University of Pittsburgh; Cambridge University; and a team composed of ICSI, SRI, and the University of Washington. EARS funded the collection of the Switchboard telephone speech corpus, which contained 260 hours of recorded conversations from over 500 speakers. The GALE program focused on Arabic and Mandarin broadcast news. Google's first effort at speech recognition came in 2007 after recruiting Nuance researchers. Its first product, GOOG-411, was a telephone-based directory service. Since at least 2006, the U.S. National Security Agency has employed keyword spotting, allowing analysts to index large volumes of recorded conversations and identify speech containing "interesting" keywords. Other government research programs focused on intelligence applications, such as DARPA's EARS program and IARPA's Babel program. In the early 2000s, speech recognition was dominated by hidden Markov models combined with feed-forward artificial neural networks (ANN). Later, speech recognition was taken over by long short-term memory (LSTM), a recurrent neural network (RNN) published by Sepp Hochreiter & Jürgen Schmidhuber in 1997. LSTM RNNs avoid the vanishing gradient problem and can learn "Very Deep Learning" tasks that require memories of events that happened thousands of discrete time steps earlier, which is important for speech. Around 2007, LSTMs trained with Connectionist Temporal Classification (CTC) began to outperform. In 2015, Google reported a 49 percent error‑rate reduction in its speech recognition via CTC‑trained LSTM. Transformers, a type of neural network based solely on attention, were adopted in computer vision and language modelling, and then to speech recognition. Deep feed-forward (non-recurrent) networks for acoustic modelling were introduced in 2009 by Geoffrey Hinton and his students at the University of Toronto, and by Li Deng and colleagues at Microsoft Research. In contrast to the prioer incremental improvements, deep learning decreased error rates by 30%. Both shallow and deep forms (e.g., recurrent nets) of ANNs had been explored since the 1980s. Howev
Multiple buffering
In computer science, multiple buffering is the use of more than one buffer to hold a block of data, so that a "reader" will see a complete (though perhaps old) version of the data instead of a partially updated version of the data being created by a "writer". It is very commonly used for computer display images. It is also used to avoid the need to use dual-ported RAM (DPRAM) when the readers and writers are different devices. == Description == === Double buffering Petri net === The Petri net in the illustration shows double buffering. Transitions W1 and W2 represent writing to buffer 1 and 2 respectively while R1 and R2 represent reading from buffer 1 and 2 respectively. At the beginning, only the transition W1 is enabled. After W1 fires, R1 and W2 are both enabled and can proceed in parallel. When they finish, R2 and W1 proceed in parallel and so on. After the initial transient where W1 fires alone, this system is periodic and the transitions are enabled – always in pairs (R1 with W2 and R2 with W1 respectively). == Double buffering in computer graphics == In computer graphics, double buffering is a technique for drawing graphics that shows less stutter, tearing, and other artifacts. It is difficult for a program to draw a display so that pixels do not change more than once. For instance, when updating a page of text, it is much easier to clear the entire page and then draw the letters than to somehow erase only the pixels that are used in old letters but not in new ones. However, this intermediate image is seen by the user as flickering. In addition, computer monitors constantly redraw the visible video page (traditionally at around 60 times a second), so even a perfect update may be visible momentarily as a horizontal divider between the "new" image and the un-redrawn "old" image, known as tearing. === Software double buffering === A software implementation of double buffering has all drawing operations store their results in some region of system RAM; any such region is often called a "back buffer". When all drawing operations are considered complete, the whole region (or only the changed portion) is copied into the video RAM (the "front buffer"); this copying is usually synchronized with the monitor's raster beam in order to avoid tearing. Software implementations of double buffering necessarily require more memory and CPU time than single buffering because of the system memory allocated for the back buffer, the time for the copy operation, and the time waiting for synchronization. Compositing window managers often combine the "copying" operation with "compositing" used to position windows, transform them with scale or warping effects, and make portions transparent. Thus, the "front buffer" may contain only the composite image seen on the screen, while there is a different "back buffer" for every window containing the non-composited image of the entire window contents. === Page flipping === In the page-flip method, instead of copying the data, both buffers are capable of being displayed. At any one time, one buffer is actively being displayed by the monitor, while the other, background buffer is being drawn. When the background buffer is complete, the roles of the two are switched. The page-flip is typically accomplished by modifying a hardware register in the video display controller—the value of a pointer to the beginning of the display data in the video memory. The page-flip is much faster than copying the data and can guarantee that tearing will not be seen as long as the pages are switched over during the monitor's vertical blanking interval—the blank period when no video data is being drawn. The currently active and visible buffer is called the front buffer, while the background page is called the back buffer. == Triple buffering == In computer graphics, triple buffering is similar to double buffering but can provide improved performance. In double buffering, the program must wait until the finished drawing is copied or swapped before starting the next drawing. This waiting period could be several milliseconds during which neither buffer can be touched. In triple buffering, the program has two back buffers and can immediately start drawing in the one that is not involved in such copying. The third buffer, the front buffer, is read by the graphics card to display the image on the monitor. Once the image has been sent to the monitor, the front buffer is flipped with (or copied from) the back buffer holding the most recent complete image. Since one of the back buffers is always complete, the graphics card never has to wait for the software to complete. Consequently, the software and the graphics card are completely independent and can run at their own pace. Finally, the displayed image was started without waiting for synchronization and thus with minimum lag. Due to the software algorithm not polling the graphics hardware for monitor refresh events, the algorithm may continuously draw additional frames as fast as the hardware can render them. For frames that are completed much faster than interval between refreshes, it is possible to replace a back buffers' frames with newer iterations multiple times before copying. This means frames may be written to the back buffer that are never used at all before being overwritten by successive frames. Nvidia has implemented this method under the name "Fast Sync". An alternative method sometimes referred to as triple buffering is a swap chain three buffers long. After the program has drawn both back buffers, it waits until the first one is placed on the screen, before drawing another back buffer (i.e. it is a 3-long first in, first out queue). Most Windows games seem to refer to this method when enabling triple buffering. == Quad buffering == The term quad buffering is the use of double buffering for each of the left and right eye images in stereoscopic implementations, thus four buffers total (if triple buffering was used then there would be six buffers). The command to swap or copy the buffer typically applies to both pairs at once, so at no time does one eye see an older image than the other eye. Quad buffering requires special support in the graphics card drivers which is disabled for most consumer cards. AMD's Radeon HD 6000 Series and newer support it. 3D standards like OpenGL and Direct3D support quad buffering. == Double buffering for DMA == The term double buffering is used for copying data between two buffers for direct memory access (DMA) transfers, not for enhancing performance, but to meet specific addressing requirements of a device (particularly 32-bit devices on systems with wider addressing provided via Physical Address Extension). Windows device drivers are a place where the term "double buffering" is likely to be used. Linux and BSD source code calls these "bounce buffers". Some programmers try to avoid this kind of double buffering with zero-copy techniques. == Other uses == Double buffering is also used as a technique to facilitate interlacing or deinterlacing of video signals.
Flexidraw
Flexidraw is a 1985 graphics computer program published by Inkwell Systems. == Gameplay == Flexidraw is a graphics program that allows users to produce drawings using a light pen and print them. == Reception == Roy Wagner reviewed the product for Computer Gaming World, and stated that "Of the many graphics programs available Flexidraw is certainly the best supported by it's [sic] parent company."