Automatic Speech

Recognition
 Automatic speech recognition
• What is the task?
• What are the main difficulties?
• How is it approached?
• How good is it?
• How much better could it be?

2/14
 What is the task?
• Getting a computer to understand spoken
language
• By “understand” we might mean
– React appropriately
– Convert the input speech into another
medium, e.g. text
• Several variables impinge on this (see
later)

3/14
 How do humans do it?

• Articulation produces
• sound waves which
• the ear conveys to the brain
• for processing
4/14
 How might computers do it?

Acoustic waveform Acoustic signal

• Digitization
• Acoustic analysis of the
Speech recognition
speech signal
• Linguistic interpretation
5/14
 What’s hard about that?
• Digitization
– Converting analogue signal into digital representation
• Signal processing
– Separating speech from background noise
• Phonetics
– Variability in human speech
• Phonology
– Recognizing individual sound distinctions (similar phonemes)
• Lexicology and syntax
– Disambiguating homophones
– Features of continuous speech
• Syntax and pragmatics
– Interpreting prosodic features
• Pragmatics
– Filtering of performance errors (disfluencies)
6/34
 Advantages
• Work processes become more efficient.
• Saves a great deal of labour.
• Improves efficiency, leads to more structured
work.
• Aiding the Visually- and Hearing-Impaired.
• Enabling Hands Free Technology.

7/14
 Disadvantages
• Lack of Accuracy and Misinterpretation
• Accents and Speech Recognition
• Background Noise Interference
• Misused with pre-recorded verbal message
• Initial training cost high and poor productivity
• Can’t be used in cubicle environment

8/14
 Conclusion
At some point in future, speech recognition may become
speech understanding.
The statistical models that allow computers to decide what
a person just said may someday allow the to grasp the
meaning behind the words.
Although it is a huge leap in terms of computational power
and software sophistication, some researchers argue that
speech recognition development offers the most direct line
from the computers of today to true artificial intelligence.

9/14