Complete power point presentation on SPEECH RECOGNITION TECHNOLOGY.
Very helpful for final year students for their seminar.
One can use this presentation as their final year seminar.
Speech Recognition is a very interesting topic for seminar.
Size: 717.51 KB
Language: en
Added: Jan 06, 2020
Slides: 20 pages
Slide Content
Speech Recognition An Overview Srijan Kumar Jha Department of ECE,UIT Burdwan
Content Introduction What is speech recognition? Block Diagram Components Types of SR system. How do Humans do Speech Recognition. How do computer do Speech Recognition. Process Applcations Benefits Drawbacks Conclusion
Already in our pockets
What is it? → That sounds simple! Voice Recording Text
Speech recognition is the process of converting an acoustic signal, captured by a microphone or a telephone, to a set of words. Also known as “automatic speech recognition” (ASR) Definition ASR
Speech Recognition Interdiciplinary Field
Voice Input Analog To Digital Acoustic Model Language Model Feedback Display Speech Engine Block Diagram of Speech R ecognition
Acoustic model Identifies phonemes from the speech sample using a probability based mathematical model. Language model Identifies words and thus sentences uttered by the speaker from the phonemes by making use of a dictionary file and grammar file. Components of speech recognition signal Analyzer Analyses the speech signal and removes the background noise thus focusing only on the speaker’s speech.
Type of speech Recognition There are two type of Speech Recognition : Speaker Dependent SR System: Work by learning the unique characteristics of a single person’s voice and depend on the speaker for training. Speaker Independent SR System: Designed to recognize anyone’s voice , so no training is involved.
How do humans do it ? Articulation produces sound waves which the ear convey to the Brain for processing.
How do computer do it ? Acoustic Waveform Acoustic Signal Speech Recognition Digitization Acoustic Analysis of Speech Signal Linguistic Interpretation
sfdsf process User Input: system catches users’ voice in the form of analog acoustic signal. Digitization: Digitize the analog signal. Phonetic Breakdown: Breaking signals into phoneme. Statistical Modeling: Mapping Phonemes to their phonetic representation using statistics model . Matching: According to Grammar , phonetic representation and Dictionary ,the system returns a word.
Process Diagram
Process ( Contd. )
Applications Health Care Military High Performance Aircrafts Air Traffic Control System Telephony- Smart-phones Customer Helpline Services Personal Computers Home Automation Automobile audio systems
Benefits Security Productivity Advantage for handicapped and blind Usability of other languages increases Personal voice macros can be created
If the system has to work under noisy environments, background noise may corrupt the original data and leads to misinterpretation. If words that are pronounced similar for example, their, there, this technology face difficulty in distinguishing them. Drawbacks
conclusion Speech Recognition System are an indispensable part of the ever-advancing field of human-computer interaction. Needs greater research to tackle various challenges. Thank You !