Speech Recognition Process

1384 Words6 Pages
Real Time Arabic Speech Recognition Abstract_ Speech recognition is the process of automatically recognizing the spoken words of person based on information content in speech signal. This paper gives an overview of the speech recognition system and its recent progress of technologies and their algorithms. Also it gives a brief description for six feature extraction techniques: Mel-frequency cepstrum (MFFCs), Neural Network (NN), Gaussian Filtering Model (GMM), Hidden Markov Models (HMMs), The SPHINX Recognizer, the SONIC Recognizer. Finally the objective of this paper is to summarize the feature extraction techniques used in speech recognition system. Keywords_ Speech Recognition; ASR; MFCC. 1. INTRODUCTION Throughout the human history,…show more content…
Speech recognition is becoming more complex and a challenging task because of this variability in the signal. These challenges are briefly explained below:- A. .Types of Speech Utterance B. Types of Speaker Model C. Types of Vocabulary A. Types of Speech Utterance 1) Isolated word An isolated-word system operates on single words at a time - requiring a pause between saying each word. 2) Connected word Connected word system are similar to isolated words but allow separate utterance to be “run together minimum pause between them. 3) Continuous speech Continuous speech recognizers allows user to speak almost naturally and a continuous speech system operates on speech in which words are connected together, i.e. not separated by pauses. 4) Spontaneous speech An ASR system with spontaneous speech ability should be able to handle a variety of natural speech features such as words being run together, "ums" and "ahs", and even slight…show more content…
Even though speech recognition technology has advanced to the point where it is used by millions of individuals for using variety of applications. The research is now focusing on ASR systems that incorporate three features: large vocabularies, continuous speech capabilities, and speaker independence. Today, there are various systems which incorporate these combinations. However, with these numerous technological barriers in developing ASR system, still it has reached the highest growth. The milestone of ASR system is given in the following table 1 [4]. Year Progress of ASR System 1952 Digit Recognizer 1976 1000 word connected recognizer with constrained grammar 1980 1000 word LSM recognizer (separate words w/o grammar) 1988 Phonetic typewriter 1993 Read texts (WSJ news) 1998 Broadcast news, telephone conversations 1998 Speech retrieval from broadcast news 2002 Rich transcription of meetings , very large vocabulary , limited tasks , controlled environment 2004 Finnish online dictation , almost unlimited vocabulary based on morphemes 2006 Machine translation of broadcast speech 2009 Quick adaptation of synthesized voice by speech recognition (in a project where TKK participates

More about Speech Recognition Process

Open Document