WIKIBOOKS
DISPONIBILI
?????????

ART
- Great Painters
- Accounting
- Fundamentals of Law
- Marketing
- Shorthand
CARS
- Concept Cars
GAMES&SPORT
- Videogames
- The World of Sports

COMPUTER TECHNOLOGY
- Blogs
- Free Software
- My Computer

- PHP Language and Applications
- Wikipedia
- Windows Vista

EDUCATION
- Education
LITERATURE
- Masterpieces of English Literature
LINGUISTICS
- American English

- English Dictionaries
- The English Language

MEDICINE
- Medical Emergencies
- The Theory of Memory
MUSIC&DANCE
- The Beatles
- Dances
- Microphones
- Musical Notation
- Music Instruments
SCIENCE
- Batteries
- Nanotechnology
LIFESTYLE
- Cosmetics
- Diets
- Vegetarianism and Veganism
NATURE
- Animals

- Fruits And Vegetables

ARTICLES IN THE BOOK

3. Altavista
4. AOL
5. Apple Macintosh
6. Application software
7. Arrow key
8. Artificial Intelligence
9. ASCII
10. Assembly language
11. Automatic translation
12. Avatar
13. Babylon
14. Bandwidth
15. Bit
16. BitTorrent
17. Black hat
18. Blog
19. Bluetooth
20. Bulletin board system
21. Byte
22. Cache memory
23. Celeron
24. Central processing unit
25. Chat room
26. Client
27. Command line interface
28. Compiler
29. Computer
30. Computer bus
31. Computer card
32. Computer display
33. Computer file
34. Computer games
35. Computer graphics
36. Computer hardware
37. Computer keyboard
38. Computer networking
39. Computer printer
40. Computer program
41. Computer programmer
42. Computer science
43. Computer security
44. Computer software
45. Computer storage
46. Computer system
47. Computer terminal
48. Computer virus
49. Computing
50. Conference call
52. Creative commons
54. Creative Technology
55. Cursor
56. Data
57. Database
58. Data storage device
59. Debuggers
60. Demo
61. Desktop computer
62. Digital divide
63. Discussion groups
64. DNS server
65. Domain name
66. DOS
69. DVD-ROM
70. DVD-RW
71. E-mail
72. E-mail spam
73. File Transfer Protocol
74. Firewall
75. Firmware
76. Flash memory
77. Floppy disk drive
78. GNU
80. GNU Project
84. Graphics
85. Graphics card
86. Hacker
87. Hacker culture
88. Hard disk
89. High-level programming language
90. Home computer
91. HTML
93. IBM
94. Image processing
95. Image scanner
96. Instant messaging
97. Instruction
98. Intel
99. Intel Core 2
100. Interface
101. Internet
102. Internet bot
103. Internet Explorer
104. Internet protocols
105. Internet service provider
106. Interoperability
108. IPod
109. Joystick
110. JPEG
111. Keyword
112. Laptop computer
113. Linux
114. Linux kernel
115. Liquid crystal display
116. List of file formats
118. Local area network
119. Logitech
120. Machine language
121. Mac OS X
122. Macromedia Flash
123. Mainframe computer
124. Malware
125. Media center
126. Media player
127. Megabyte
128. Microsoft
129. Microsoft Windows
130. Microsoft Word
131. Mirror site
132. Modem
133. Motherboard
134. Mouse
136. Mozilla Firefox
137. Mp3
138. MPEG
139. MPEG-4
140. Multimedia
141. Musical Instrument Digital Interface
142. Netscape
143. Network card
144. News ticker
145. Office suite
146. Online auction
147. Online chat
148. Open Directory Project
149. Open source
150. Open source software
151. Opera
152. Operating system
153. Optical character recognition
154. Optical disc
155. output
156. PageRank
158. Pay-per-click
159. PC speaker
160. Peer-to-peer
161. Pentium
162. Peripheral
163. Personal computer
164. Personal digital assistant
165. Phishing
166. Pirated software
167. Podcasting
168. Pointing device
169. POP3
170. Programming language
171. QuickTime
172. Random access memory
173. Routers
174. Safari
175. Scalability
176. Scrollbar
177. Scrolling
178. Scroll wheel
179. Search engine
180. Security cracking
181. Server
182. Simple Mail Transfer Protocol
183. Skype
184. Social software
185. Software bug
186. Software cracker
187. Software library
188. Software utility
189. Solaris Operating Environment
190. Sound Blaster
191. Soundcard
192. Spam
193. Spamdexing
194. Spam in blogs
195. Speech recognition
196. Spoofing attack
198. Spyware
199. Streaming media
200. Supercomputer
201. Tablet computer
202. Telecommunications
203. Text messaging
204. Trackball
205. Trojan horse
206. TV card
207. Unicode
208. Uniform Resource Identifier
209. Unix
210. URL redirection
211. USB flash drive
212. USB port
213. User interface
214. Vlog
215. Voice over IP
216. Warez
217. Wearable computer
218. Web application
219. Web banner
220. Web browser
221. Web crawler
222. Web directories
223. Web indexing
224. Webmail
225. Web page
226. Website
227. Wiki
228. Wikipedia
229. WIMP
230. Windows CE
231. Windows key
232. Windows Media Player
233. Windows Vista
234. Word processor
235. World Wide Web
236. Worm
237. XML
238. X Window System
239. Yahoo
240. Zombie computer

MY COMPUTER
http://en.wikipedia.org/wiki/Speech_recognition

All text is available under the terms of the GNU Free Documentation License: http://en.wikipedia.org/wiki/Wikipedia:Text_of_the_GNU_Free_Documentation_License

# Speech recognition

Speech recognition (in many contexts also known as 'automatic speech recognition', computer speech recognition or erroneously as Voice Recognition) is the process of converting a speech signal to a sequence of words, by means of an algorithm implemented as a computer program. Speech recognition applications that have emerged over the last years include voice dialing (e.g., Call home), call routing (e.g., I would like to make a collect call), simple data entry (e.g., entering a credit card number), and preparation of structured documents (e.g., a radiology report).

Voice Verification or speaker recognition is a related process that attempts to identify the person speaking, as opposed to what is being said.

## Speech recognition technology

In terms of technology, most of the technical text books nowadays emphasize the use of Hidden Markov Model as the underlying technology. The dynamic programming approach, the neural network-based approach and the knowledge-based learning approach have been studied intensively in the 1980s and 1990s.

## Performance of speech recognition systems

The performance of a speech recognition systems is usually specified in terms of accuracy and speed. Accuracy is measured with the word error rate, whereas speed is measured with the real time factor.

Most speech recognition users would tend to agree that dictation machines can achieve very high performance in controlled conditions. Part of the confusion mainly comes from the mixed usage of the term speech recognition and dictation.

Speaker-dependent dictation systems requiring a short period of training can capture continuous speech with a large vocabulary at normal pace with a very high accuracy. Most commercial companies claim that recognition software can achieve between 98% to 99% accuracy (getting one to two words out of one hundred wrong) if operated under optimal conditions. These optimal conditions usually means the test subjects have 1) matching speaker characteristics with the training data, 2) proper speaker adaptation, and 3) clean environment (e.g. office space). (This explains why some users, especially accented, might actually find that the recognition rate could be perceptually much lower than the expected 98% to 99%).

Other, limited vocabulary, systems requiring no training can recognize a small number of words (for instance, the ten digits) from most speakers. Such systems are popular for routing incoming phone calls to their destinations in large organizations.

## Noisy channel formulation of statistical speech recognition

Many modern approaches such as HMM-based and ANN-based speech recognition are based on noisy channel formulation (See also Alternative formulation of speech recognition). In that view, the task of a speech recognition system is to search for the most likely word sequence given the acoustic signal. In other words, the system is searching for the most likely word sequence $\tilde{W}$ among all possible word sequences W * from the acoustic signal A (what some will call the observation sequence according to the Hidden Markov Model terminology).

$\tilde{W} = arg max_{W \in W^*} \Pr(W | A)$

Based on Bayes' rule, the above formulation could be rewritten as

$\tilde{W} = arg max_{W \in W^*} \frac{\Pr(A |W) \Pr(W)}{\Pr(A)}$

Because the acoustic signal is common regardless of which word sequence chosen, the above could be usually simplified to

$\tilde{W} = arg max_{W \in W^*} \Pr(A |W) \Pr(W)$

The term $\Pr(A|W)$ is generally called acoustic model. The term $\Pr(W)$ is generally known as language model.

Both acoustic modeling and language modeling are important studies in modern statistical speech recognition. In this entry, we will focus on explaining the use of hidden Markov model (HMM) because notably it is very widely used in many systems. (Language modeling has many other applications such as smart keyboard and document classification; please refer to the corresponding entries.)

## Approaches of statistical speech recognition

### Hidden Markov model (HMM)-based speech recognition

Modern general-purpose speech recognition systems are generally based on hidden Markov models (HMMs). This is a statistical model which outputs a sequence of symbols or quantities.

One possible reason why HMMs are used in speech recognition is that a speech signal could be viewed as a piece-wise stationary signal or a short-time stationary signal. That is, one could assume in a short-time in the range of 10 milliseconds, speech could be approximated as a stationary process. Speech could thus be thought as a Markov model for many stochastic processes (known as states).

Another reason why HMMs are popular is because they can be trained automatically and are simple and computationally feasible to use. In speech recognition, to give the very simplest setup possible, the hidden Markov model would output a sequence of n-dimensional real-valued vectors with n around, say, 13, outputting one of these every 10 milliseconds. The vectors, again in the very simplest case, would consist of cepstral coefficients, which are obtained by taking a Fourier transform of a short-time window of speech and decorrelating the spectrum using a cosine transform, then taking the first (most significant) coefficients. The hidden Markov model will tend to have, in each state, a statistical distribution called a mixture of diagonal covariance Gaussians which will give a likelihood for each observed vector. Each word, or (for more general speech recognition systems), each phoneme, will have a different output distribution; a hidden Markov model for a sequence of words or phonemes is made by concatenating the individual trained hidden Markov models for the separate words and phonemes.

The above is a very brief introduction to some of the more central aspects of speech recognition. Modern speech recognition systems use a host of standard techniques which it would be too time consuming to properly explain, but just to give a flavor, a typical large-vocabulary continuous system would probably have the following parts. It would need context dependency for the phones (so phones with different left and right context have different realizations); to handle unseen contexts it would need tree clustering of the contexts; it would of course use cepstral normalization to normalize for different recording conditions and depending on the length of time that the system had to adapt on different speakers and conditions it might use cepstral mean and variance normalization for channel differences, vocal tract length normalization (VTLN) for male-female normalization and maximum likelihood linear regression (MLLR) for more general speaker adaptation. The features would have delta and delta-delta coefficients to capture speech dynamics and in addition might use heteroscedastic linear discriminant analysis (HLDA); or might skip the delta and delta-delta coefficients and use LDA followed perhaps by heteroscedastic linear discriminant analysis or a global semitied covariance transform (also known as maximum likelihood linear transform (MLLT)). A serious company with a large amount of training data would probably want to consider discriminative training techniques like maximum mutual information (MMI), MPE, or (for short utterances) MCE, and if a large amount of speaker-specific enrollment data was available a more wholesale speaker adaptation could be done using MAP or, at least, tree-based maximum likelihood linear regression. Decoding of the speech (the term for what happens when the system is presented with a new utterance and must compute the most likely source sentence) would probably use the Viterbi algorithm to find the best path, but there is a choice between dynamically creating combination hidden Markov models which includes both the acoustic and language model information, or combining it statically beforehand (the AT&T approach, for which their FSM toolkit might be useful). Those who value their sanity might consider the AT&T approach, but be warned that it is memory hungry.

### Neural network-based speech recognition

Another approach in acoustic modeling is the use of neural networks. They are capable of solving much more complicated recognition tasks, but do not scale as well as HMMs when it comes to large vocabularies. Rather than being used in general-purpose speech recognition applications they can handle low quality, noisy data and speaker independence. Such systems can achieve greater accuracy than HMM based systems, as long as there is training data and the vocabulary is limited. A more general approach using neural networks is phoneme recognition. This is an active field of research, but generally the results are better than for HMMs. There are also NN-HMM hybrid systems that use the neural network part for phoneme recognition and the hidden markov model part for language modeling.

### Dynamic time warping (DTW)-based speech recognition

Main article: Dynamic time warping

Dynamic time warping is an algorithm for measuring similarity between two sequences which may vary in time or speed. For instance, similarities in walking patterns would be detected, even if in one video the person was walking slowly and if in another they were walking more quickly, or even if there were accelerations and decelerations during the course of one observation. DTW has been applied to video, audio, and graphics -- indeed, any data which can be turned into a linear representation can be analysized with DTW.

A well known application has been automatic speech recognition, to cope with different speaking speeds. In general, it is a method that allows a computer to find an optimal match between two given sequences (e.g. time series) with certain restrictions, i.e. the sequences are "warped" non-linearly to match each other. This sequence alignment method is often used in the context of hidden Markov models.

### Knowledge-based speech recognition

This method uses a stored data base of commands that compares simple words with ones in the data base.

## For further information

Popular speech recognition conferences held each year or two include ICASSP, Eurospeech/ICSLP (now named Interspeech) and the IEEE ASRU. Conferences in the field of Natural Language Processing, such as ACL, NAACL, EMNLP, and HLT, are beginning to include papers on speech processing. Important journals include the IEEE Transactions on Speech and Audio Processing (now named IEEE Transactions on Audio, Speech and Language Processing), Computer Speech and Language, and Speech Communication. Books like "Fundamentals of Speech Recognition" by Lawrence Rabiner can be useful to acquire basic knowledge but may not be fully up to date (1993). Another good source can be "Statistical Methods for Speech Recognition" by Frederick Jelinek which is a more up to date book (1998). Keep an eye on government sponsored competitions such as those organised by DARPA (the telephone speech evaluation was most recently known as Rich Transcription). In terms of freely available resources, the HTK book (and the accompanying HTK toolkit) is one place to start to both learn about speech recognition and to start experimenting (if you are very brave). You could also search for Carnegie Mellon University's SPHINX toolkit.

## Applications of speech recognition

• Command recognition - Voice user interface with the computer
• Dictation
• Interactive Voice Response
• Automotive speech recognition
• Medical Transcription [1]
• Pronunciation Teaching in computer-aided language learning applications
• Automatic Translation

• Guided Speech IVR
• Speech processing
• Audio visual speech recognition
• Speech verification
• Speaker identification
• Speech synthesis
• Speech Analytics
• Keyword spotting
• VoiceXML
• Macfarlane's Law - the conflict between typing and reading speed anticipated the importance of speech recognition

## References

• "Survey of the State of the Art in Human Language Technology (1997) by Ron Cole et all"

## Books

• Multilingual Speech Processing, Edited by Tanja Schultz and Katrin Kirchhoff, April 2006--Researchers and developers in industry and academia with different backgrounds but a common interest in multilingual speech processing will find an excellent overview of research problems and solutions detailed from theoretical and practical perspectives.---CH 1: Introduction / CH 2: Language Characteristics / CH 3: Linguistic Data Resources / CH 4: Multilingual Acoustic Modeling / CH 5: Multilingual Dictionaries / CH 6: Multilingual Language Modeling / CH 7: Multilingual Speech Synthesis / CH 8: Automatic Language Identification / CH 9: Other Challenges /

• NIST Speech Group
• Sphinx Open Source Speech Recognition Engine
• Entropic/Cambridge Hidden Markov Model Toolkit
• Julius Open Source Speech Recognition Engine
• The SPRACHcore software package
• Open CV library, especially the multi-stream speech and vision combination programs
• Xvoice: Speech control of X applications
• LT-World: Portal to information and resources on the internet
• LDC – The Linguistic Data Consortium
• Evaluations and Language resources Distribution Agency
• OLAC – Open Language Archives Community
• BAS – Bavarian Archive for Speech Signals
• VoxForge - Free GPL Speech Corpus and Acoustic Model repository