The Demo / Kemo corpus A principled approach to the study of - - PowerPoint PPT Presentation

the demo kemo corpus
SMART_READER_LITE
LIVE PREVIEW

The Demo / Kemo corpus A principled approach to the study of - - PowerPoint PPT Presentation

The Demo / Kemo corpus A principled approach to the study of cross-cultural differences in the vocal expression and perception of emotion Martijn Goudbeek Mirjam Broersma University of Tilburg MPI for Psycholinguistics LREC, Valetta, 19-21


slide-1
SLIDE 1

The Demo / Kemo corpus

A principled approach to the study of cross-cultural differences in the vocal expression and perception of emotion

Mirjam Broersma MPI for Psycholinguistics LREC, Valetta, 19-21 May 2010 Martijn Goudbeek University of Tilburg

slide-2
SLIDE 2

Two designs in cross-cultural perception of emotion: One-to-many and many-to-one

The Kemo / Demo corpus: Many-to-many Corpus construction Future plans and discussion

slide-3
SLIDE 3

Cross-cultural perception of emotion

  • Basic emotions (joy, anger, fear, disgust, sadness) are

recognized well above chance between cultures

  • Other emotions (pride, shame, pleasure) depend more on

cultural factors

slide-4
SLIDE 4

Cross-cultural perception of emotion

  • Most of this research has been done in the facial domain
  • The vocal domain is interesting since it simultaneously

communicates linguistic content and emotional meaning

  • The field has addressed the study of cross-cultural

emotion perception with two research designs

slide-5
SLIDE 5

Many-to-one versus One-to-many Many-to-one versus One-to-many Two approaches to constructing corpora in the study of cross-cultural differences in the vocal expression of emotion Many-to-one and One to many designs

slide-6
SLIDE 6

Many-to-one versus One-to-many Many-to-one versus One-to-many One-to-many design Use an existing corpus of emotional expression that has been developed and validated in one language to assess the ability of speakers from

  • ne or more other languages to successfully

decode the emotional expressions

slide-7
SLIDE 7

Many-to-one versus One-to-many Many-to-one design Develop and validate a corpus in several languages and then present the expressions to listeners from one language

slide-8
SLIDE 8

Many-to-one versus One-to-many

L4 L2 L3 L1

Listeners Speakers

L1 L3 L4 L2

Speakers Listeners

slide-9
SLIDE 9

Many-to-one versus One-to-many

  • Neither design unambiguously separates

effects of language and emotion:

  • Emotions are expressed with non-native

phonetic characteristics

  • There are no within language controls that

listen to both the L1 and L2 versions

  • Solution: a many-to-many design
slide-10
SLIDE 10

Many-to-many

L1 L2 L2 L1

Speakers Listeners

slide-11
SLIDE 11
  • Dutch and Korean actors
  • 8 emotions x 8 actors (4 M, 4 F) x 2 languages
  • Carrier phrase: “nutohom seppikang”
  • Meaningless in both languages
  • Phonetically / phonotactically possible in both

languages

  • No embedded words

The Demo / Kemo corpus

slide-12
SLIDE 12

The Demo / Kemo corpus

Valence A r

  • u

s a l Positive Negative High Joy Anger Pride Fear Low Tenderness Sadness Relief Irritation

Emotions

slide-13
SLIDE 13

The Demo / Kemo corpus Recording sessions

  • Scenario approach, but also free improvisation
  • In interaction with a stage director
  • Order of emotions randomized over actors
  • Four valid emotion portayals
  • Validation by forced choice identification
slide-14
SLIDE 14

The Demo / Kemo corpus Examples

slide-15
SLIDE 15

The Demo / Kemo corpus Validation study

  • 24 listeners from each language

(Nijmegen and Seoul)

  • 8 emotions x 8 speakers x 4

repetitions = 256 utterances per language

  • Praat MFC experiment with

naturalness rating

  • Results expressed in unbiased

hitrates

slide-16
SLIDE 16

Corpus construction

  • From the four rated portrayals the best two were

selected based on

  • The unbiased hitrate (Hu)
  • Confusions with other emotions
  • Goodness ratings
  • Chance (if all else failed)
  • This resulted in a corpus with 256 expressions
slide-17
SLIDE 17

Corpus construction Average unbiased hitrates

Anger Fear Sadness Joy Irritation Pride Relief Tenderness 0.1 0.2 0.3 0.4 0.5 0.6

Emotion Unbiased hitrate

Dutch Korean

slide-18
SLIDE 18

Corpus construction Statistical analysis

  • Significant effect of emotion: some emotions are better recognized

than others

  • No significant effect of language
  • No significant interaction between language and emotion
  • Conclusion: quality of recordings equally well for both languages /

all emotions recognized equally well in both languages

slide-19
SLIDE 19

Future plans and discussion Many-to-many perception experiment

L1 L2 L2 L1

slide-20
SLIDE 20

Future plans and discussion

  • Acoustic analysis; duration
  • Several small corpora or one big one?
  • Availability: email the authors:

mirjam@mirjambroersma.nl m.b.goudbeek@uvt.nl