Abstract:

Classical automatic speech recognition (ASR) systems are based on well-developed feature sets which provide satisfactory representations of phonetic units. On the other hand, studies on prosody demonstrate how long-term acoustic features transport important meaning. Based on available ASR Kaldi recipes for conversational Austrian German, this work compares different feature extraction methods by adding acoustic features which relate to prosody to given baseline systems.

Contact:

Julian Linke (linke@tugraz.at) Barbara Schuppler (b.schuppler@tugraz.at)