SPECTRUM?

1
SPECTRUM?

• Hynek Hermansky
• with
• Jordan Cohen, Sangita Sharma, and Pratibha Jain,

2
/u/ /o/ /a/ /e/ /iy/
limited commercial success -John Pierce 1969
3
SHORT TERM SPECTRUM
4
Cortical receptive fields
5
ASR from TempoRAl Patterns (TRAP)
6
WHY 200-1000 ms ?
200 1000 ms
frequency
time

• because thats where the information is
  (coarticulation)
• mutual info studies (Bilmes, Yang et al.)
• psychophysics of hearing
• 200 ms critical time window (forward masking,
  perception of loudness, perception of gaps,
• physiology of hearing
• time component of cortical receptive fields
  (Klein)
• because it works
• ETSI Aurora work

7
WHY narrow frequency bands?
frequency
time
1-3 Bark

• psychophysics of hearing
• independence of processing within critical bands
• physiology of hearing
• mechanical selectivity of cochlea
• cortical receptive fields (e.g. Shamma)
• because it works
• multi-band ASR (Bourlard and Dupont, Hermansky et
  al,)
• decrease in ASR accuracy for wider frequency
  spans (Jain and Hermansky - Eurospeech 2003)

8
Which features?
frequency
time
data-guided processing
features

• no knowledge is better than wrong knowledge
• data cannot lie
• speech evolved to be heard
• data-derived processing is consistent with
  human-like processing (minus the irrelevant
  components of the human cognitive processing)

9
WHY data-guided processing?
frequency
time
data-guided (trained on data) processing
features

• some function of class posteriors
• class posteriors form the most efficient feature
  set e.g. Fukunaga
• posteriors of which classes?

10
Speech Events
class (phoneme?) detection
11
(No Transcript)