First there were punch cards. Then keyboards. Next came the mouse. The exponentially growing power of computers may call for a new, more elegant way of inputing data. Wouldn't it be nice to say "Computer, Open Netscape", or dictate a paper into a text editor instead of typing?
We plan on using Formant Analysis and Pitch Determination in exploring speech interpretation. The Formant Analysis will use common properties of vowel sound to determine the vowel being spoken. Pitch Determination techniques will be used to find the pitch of the speakers impulse train and can lead to identification. We also hope to fuse the two methods to produce more accurate readings in both categories (i.e. determining what was said can be better determined if we have prior knowledge of who the speaker was).
Using Matlab extensively, we will build (program) an interpreter. We will analyze vowel sounds extracted from speech signals of words like "bob", "hood" and "hawed" by isolating the formant frequencies of the sounds. We will also explore our system's ability to differentiate between speakers by extracting the impulse train from resonant vowel sounds and determine pitch. Finally we hope to develop a process that will be able to extract vowels from words, determine what those words were, and who the speaker was.
Probelms we hope to tackle:
1. Extracting Vowel Sounds
2. Identifying Vowel Sounds
3. Identifying a Speaker