Speech recognition (in many contexts, also known as automatic speech recognition, computer speech recognition or voice recognition) is the process of converting a speech signal to a set 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).

Defining the Problem

---

According to "Survey of the State of the Art in Human Language Technology (1997) by Ron Cole et all" Speech recognition is the process of converting an acoustic signal, captured by a microphone or a telephone, to a set of words. The recognized words can be the final results, for such applications as commands & control, data entry, and document preparation. They can also serve as the input to further linguistic processing in order to achieve text formating or speech understanding.

Speech recognition systems can be characterized by many parameters as in the table below.

Parameters	Range
Speaking Mode	Isolated words to continuous speech
Speaking Style	Read speech to spontaneous speech
Enrollment	Speaker-dependent to Speaker-independent
Vocabulary	Small (< 20 words) to large (> 20,000 words)
Language Model	Finite-state to context-sensitive
Perplexity	Small (< 10) to large (> 100)
SNR	High (> 30 dB) to low (< 10 dB)
Transducer	Voice-cancelling microphone to telephone

An isolated-word speech recognition system requires that the speaker pause briefly between words, whereas a continuous speech recognition system does not. Spontaneous, or extemporaneously generated, speech contains disfluencies and is much more dificult to recognize than speech read from script. Some systems require speaker enrollment (a user must provide samples of his or her speech before using them) whereas other systems are said to be speaker-independent, in that no enrollment is necessary. Some of the other parameters depend on the specific task. Recognition is generally more difficult when vocabularies are large or have many similar-sounding words. When speech is produced in a sequence of words, language models or artificial grammars are used to restrict the combination of words. The simplest language model can be specified as a finite-state network, where the permissible words following each word are explicitly given. More general language models approximating natural language are specified in terms of a context-sensitive grammar. One popular measure of the difficulty of the task, combining the vocabulary size and the language model, is perplexity, loosely defined as the geometric mean of the number of words that can follow a word after the language model has been applied. In addition, there are some external parameters that can affect speech recognition system performance, including the characteristics of the environmental noise and the type and the placement of the microphone.

More on [ Speech recognition ]

Linux Today

Google Unveils Chrome Source Code and Linux port
Sun, 07 Sep 2008 00:01:02 -0000
ars Technica: "In conjunction with the release, Google has also launched Chromium, an open-source software project that enables third-party developers to study, modify, extend, and redistribute the underlying source code of the Chrome browser."
Selling GNU/Linux in a Box
Sat, 06 Sep 2008 20:01:39 -0000
Linux.com: "Eight years ago, computer stores stocked a choice of GNU/Linux distributions -- established ones like Caldera, Red Hat, and SUSE, and newcomers like Corel, Progeny, and Stormix. Now, only Ubuntu and openSUSE offer box sets, and both face challenges that other distributions found unsolvable..."
10 Open Source Companies to Watch
Sat, 06 Sep 2008 19:01:39 -0000
Network World: "The decision is no longer a question of open source, but about what product is best at solving computing problems regardless of how it was built."
Centralized Access With iSCSI Wraps it up: Open Source SANs, part 4
Sat, 06 Sep 2008 18:01:39 -0000
Search Enterprise Linux: "If you've read the three previous parts of this tip, you should now have two servers running and a Distributed Replicated Block Device (DRBD) available between them. The iSCSI target service will draw the two servers and DRBD together to create a fully functional SAN."
Adding Heartbeat to Your Open Source SAN: Open Source SANs, part 3
Sat, 06 Sep 2008 17:01:39 -0000
Search Enterprise Linux: "Heartbeat is a monitoring tool that will help you to make the most of your SAN by catching problems before they interfere with your productivity. Part three of this four-part tip shows you how to install a Heartbeat cluster in an open source SAN."
Setting up DRBD in an Open Source SAN: Open Source SANs, part 2
Sat, 06 Sep 2008 16:01:39 -0000
Search Enterprise Linux: "As we established in part one of this series on open storage area networks (SANs), building an open source SAN provides a cost-effective alternative for companies with a tight budget. Now that we've established the merits and some of the important considerations in creating open source SANs, we'll explain how to set up the Distributed Replicated Block Device (DRBD) service, which allows for replicated storage in a SAN."

Subscribe to Linux RSS feed