lecture28

lecture28 - Speech Recognition; page 1 of 8 Artificial...

Info iconThis preview shows pages 1–4. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Speech Recognition; page 1 of 8 Artificial Intelligence Speech Recognition Russell and Norvig, Chapter 15.6 (short overview only) Speech Recognition; page 2 of 8 Analog acoustic signal: Sampled, quantized digital signal: Frames with features: 10 15 38 52 47 82 22 63 24 89 94 11 10 12 73 Frames with vector quantization values: C82 C44 C63 C25 C39 phones words (problems: segmentation, homophones) meaning 8-16 kHz 8-12 bits 10 msecs features: amount of energy in frequency ranges etc. c1 c2 c3 Speech Recognition; page 3 of 8 Vowels Consonants B-N Consonants P-Z Phone Example Phone Example Phone Example [iy] b ea t [b] b et [p] p et [ih] b i t [ch] Ch et [r] r at [ey] b e t [d] d ebt [s] s et [ae] b a t [f] f at [sh] sh oe [ah] b u t [g] g et [t] t en [ao] b ough t [hh] h at [th] th ick [ow] b oa t [hv] h igh [dh] th at [uh] b oo k [jh] j et [dx] bu tt er [ux] b eau ty [k] k ick [v] v et [er] B er t [l] l et [w] w et [ay] b uy [el] bott le [wh] wh ich [oy] b oy [m] m et [y] y et [axr] din er...
View Full Document

Page1 / 8

lecture28 - Speech Recognition; page 1 of 8 Artificial...

This preview shows document pages 1 - 4. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online