preview

Strengths And Weaknesses Of Speech Recognition

Decent Essays

CHAPTER 1
INTRODUCTION
People use calculators to perform calculations that have a numeric keypad to input the data and a display to get the result. To overcome this, speech signal can be used to input the data and the result is an audio signal.
Speech is the vocalized form of human communication. It ranges from 90 Hz to 7,000 Hz. Each spoken word is created out of the phonetic combination of a limited set of vowel and consonant speech sound units. The voiced speech of a typical adult male will have a fundamental frequency from 85 to 180 Hz, and that of a typical adult female from 165 to 255 Hz. Thus, the fundamental frequency of most speech falls below the bottom of the "voice frequency" band as defined above.
Speech recognition is a process …show more content…

Generally the more traing, the higher the perfromance of the system for virtually any task. The reference pattern are sensitive to the speaking environment and transmission characteristics of the medium used to create the speech, this is because the speech spectral characteristics are affected by transmission and background noise. No speech-specific knowledge is used explicitly in the system; hence the method is relatively in sensitive to choice of vocabulary words, task, syntax, and task semantics. The computational load for both pattern training and pattern classification is generally linearly proportional to the number of patterns being trained or recognized. Hence computation for a large number of sound classes could and often does become prohibitive. Because the system is insensitive to sound class, the basic techniques are applicable to a wide range of speech sounds, including phrases, whole words and sub word units. The basic set of techniques developed for one sound class (e.g., words) can generally be directly applied to different sound classes (e.g., subword units) with little or no modifications to the

Get Access