Questions and Answers Regarding Artificial Intelligence Essays

Speech is often based on concatenation of natural speech i.e units, that are taken from natural speech put together to form a word or sentence. Concatenative speech synthesis .has become very popular in recent years due to its improved

Discussions about artificial intelligence catch people’s attention. Over the last few decades, products of artificial intelligence have become commonplace in the lives of every day. People use GPS systems like Google

Speech recognition is necessary to recognize when things happen. Ordering or arranging things is something workers have to do. Childcare

Inevitably Artificial Intelligence has, and will continue to affecting our lives. Artificial Intelligence (AI) Effort to develop computer-based systems:  that behave like humans:  learn languages  accomplish physical tasks  use a perceptual apparatus With the development of practical techniques based on AI research, advocates of AI have argued that opponents of AI have repeatedly changed their position on tasks such as computer chess or speech recognition that were previously regarded as "intelligent" in order to deny the accomplishments of AI. They point out that this moving of the goalposts effectively defines "intelligence" as "whatever humans can do that machines cannot". A speech recognition system is a type of software that allows the user to have their spoken words converted into written text in a computer application such as a word processor or spreadsheet. The computer can also be controlled by the use of spoken commands. Speech recognition software can be installed on a personal computer of appropriate specification. The user speaks into a microphone (a headphone microphone is usually supplied with the product). The software generally requires an initial training and enrolment process in order to teach the software to recognize the voice of the user. A voice profile is then produced that is unique to that individual. This procedure also helps the user to learn how to speak to a computer.

There are two types of innovation, incremental innovations which improving existing products or practices, but IBM’s research teams are encouraged to take on “grand challenges,” challenges that drive science. These grand challenges produce radical innovations which provide new and very different solutions; the development of Watson was no exception. Watson is a competence enhancing innovation for IBM and is built on existing knowledge from IBM’s research in AI. AI’s S-curve in technology improvement has been slow to improve mainly because it has been poorly understood. Language is one of the areas concerning AI that has been the slowest to improve. As humans we relate words, images, phrases, and ideas back into the way we think which is called natural language. Since the begging of the computer era people have expected computers to be able to understand and speak in natural language, however so far computers have failed to be able to do so. Natural language is very complex, something that computers have a hard time following. Computers are used to clear-cut commands in language where as human language is something different. In the development of Watson the

(i) The Speech Input Device The “Microphones - Speech Recognition” is a speech Input device. To operate it we require using a microphone to talk to the computer. Also we need to add a sound card to the computer. The Sound card digitizes audio input into 0/1s .A speech recognition program can process the input and convert it into machine-recognized commands or input.

Emergence networks mimics biological nervous system unleash generations of inventions and discoveries in the artificial intelligent field. These networks have been introduced by McCulloch and Pitts and called neural networks. Neural network’s function is based on principle of extracting the uniqueness of patterns through trained machines to understand the extracted knowledge. Indeed, they gain their experiences from collected samples for known classes (patterns). Quick development of neural networks promotes concept of the pattern recognition by proposing intelligent systems such as handwriting recognition, speech recognition and face recognition. In particular, Problem of handwriting recognition has been considered significantly during

IV. PATTERN RECOGNITION USING NEURAL NETS For really complex problems neural networks outperform their competition. With the aid of GPU’s [1], the neural networks can be trained faster than ever before. Deep learning is specially used to train computers to recognize patterns.

In this paper, a voice guidance system for autonomous robots is proposed as a project based on microcontroller. The proposed system consists of a microcontroller and voice recognition software that can recognize a limited number of voice patterns. The commands of autonomous robots are classified and are organized such that one voice recognition software can distinguish robot commands under each directory. Thus, the proposed system can distinguish more voice commands than one voice recognition processor can.

In order to obtain relevant speaker features, the vectors are analyzed towards characteristic factors. Thereby, a factor analysis model is iteratively trained. The factor analyzed features are referred to as identity-vectors (i-vectors).To obtain the i-vectors, first a speech Universal Background Model (UBM) is trained on a training data. The UBM is a GMM with large number of Gaussians, so that it captures all possible variabilities in speech in the feature space. In the proposed system the TIMIT and TIFR datasets have been used for the UBM training.

As technology advances, the research of digital signal processing is undergoing rapid development. At present, it has been used in many fields such as communications industry, voice and acoustics applications, radar and image. The processing of the speech signal is one of the key areas of DSP application. So far, it has formed a number of research directions, such as speech analysis, speech enhancement, speech recognition, voice communication, etc..

account [2]. These basic features can basically ensure that classification, but there is still much room for improvement. Therefore, some researchers have proposed some new features, such as harmony features [2]. Some researchers also consider in combination acoustic features with other speech features such as semantic features (individual keywords), and facial expression could be a good choice. Dimensionality reduction is indispensable, thus the second issue is further to get optimal features sets with minimal completeness. This stage aims to reduce the size of the extracted speech feature set by selecting the most valuable subset of features and removing the irrelevant ones. Its not easy to give universal and effec-

Note that there may be incorrect spellings, punctuation and/or grammar in this document. This is to allow correct pronunciation and timing by a speech synthesiser.

1.1.4 Speech recognition [b]: In speech recognition take a sound clip of the person and determine the textual representation of speech.

The ChantSR class simplifies the process of recognizing speech by handling the low-level activities directly with a recognizer