Acoustic correlates of frustration in spontaneous speech

The focus of this master’s thesis by the first author was to investigate the acoustic attributes of frustration in spontaneous speech. The speech material was recorded from real life Swedish telephone services by the company Voice Provider. The utterances were selected speaker by speaker in order to have at least one of them judged as emotionally neutral by a listener group, while the other utterances of the same speaker were judged as displaying emotional speech. Due to the nature of the speech material most of it was spoken in a neutral way. However, some percent of the utterances displayed various degrees of frustration, mostly anger but also some despondency, and these were the emotions studied in this report. We also studied the emotional intensity of the utterances. Acoustic cues of the emotional speech were compared to those of neutral speech for the same speaker. We found some significant differences between the acoustic cues for neutral and emotional speech. Anger was characterized by a rise of fundamental frequency and an increase in speech amplitude, whereas despondency reduced the syllable rate significantly. The emotional intensity raised the pitch, increased the amplitude and decreased the syllable rate. Correlations were also found between perceived emotions and acoustic speech parameters.