Session Voice Quality I:

Voice Quality I

Type: oral
Chair: John Esling
Date: Tuesday - August 07, 2007
Time: 13:20
Room: 5 (Blue)


Voice Quality I-1 Detection of Irregular Phonation in Speech
Srikanth Vishnubhotla, Institute for Systems Research, University of Maryland
Carol Y. Espy-Wilson, Institute for Systems Research, University of Maryland
Paper File
  The problem addressed here is that of detecting irregular phonation during conversational speech. While most published work tackles this problem only by focusing on the voiced regions of speech, we focus on detecting irregular phonation without assuming prior knowledge of voiced regions. In addition, we improve the pitch estimation accuracy of a current pitch tracking algorithm in regions of irregular phonation, where most pitch trackers fail to perform well. The algorithm has been tested on the TIMIT and NIST 98 databases. The detection rate for the TIMIT database is 91.8% (17.42% false detections). The detection rate for the NIST 98 database is 91.5% (12.8% false detections). The pitch detection accuracy increased from 95.4% to 98.3% for the TIMIT database, and from 94.8% to 97.4% for the NIST 98 database.
Voice Quality I-2 Acoustic and EGG analysis of pressed phonation
Carlos Toshinori Ishi, ATR - IRC Labs.
Hiroshi Ishiguro, ATR - IRC Labs.
Norihiro Hagita, ATR - IRC Labs.
Paper File
  Pressed phonation ("rikimi" in Japanese) is a voice quality that carries important paralinguistic information of expressivity in the emotional or attitudinal states of the speaker. Analysis of pressed voice samples extracted from natural conversational speech firstly shows that irregularity in periodicity (such as in vocal fry and harsh voices) is a common but not a strictly determinant feature of pressed voices. Spectral analysis shows that parameters related with spectral slope are effective to identify part of the pressed voice samples, but fail when vowels are nasalized or double-beating occurs within a glottal cycle. Temporal analyses of speech and EGG waveforms indicate that information about the completely closed period can potentially be used for pressed voice identification.
Christel De Bruijn, University of Central England, Birmingham, UK
Sandra Whiteside, University of Sheffield, UK
Paper File
  This study investigates the effect of a speech recognition task on acoustic measures of voice quality. Type of speech recogntion (discrete and continuous) and vocal load of a speaker receive particular attention. A rise in F0, a common finding in voice fatigue studies, appears as the most consistent finding. It is interpreted as part of hyperfunctional mechanism countering early signs of voice fatigue.

Back to Conference Schedule