3. Speech signal analysis
We have already noted the great redundancy of the speech signal. In automatic speech processing, this redundancy needs to be reduced, using appropriate processing techniques to reduce processing times and memory requirements. In addition, and sometimes simultaneously, speech signal processing can be used to extract parameters relevant to recognition (characteristics of noisy sounds, formant frequencies, etc.).
A vowel can be characterized by three given frequency zones, called formants. The formant frequencies of sounds such as vowels and certain voiced consonants correspond to the maximum energy in the spectrum of these sounds, i.e. approximately to the resonant frequencies of the vocal tract in the corresponding configuration.
The devices used can be analog: however, with the evolution of digital...
Exclusive to subscribers. 97% yet to be discovered!
Already subscribed? Log in!
Speech signal analysis
Word recognition
Article included in this offer
"Digital documents and content management"
(
75 articles
)
Updated and enriched with articles validated by our scientific committees
A set of exclusive tools to complement the resources
Bibliography
Exclusive to subscribers. 97% yet to be discovered!
Already subscribed? Log in!
