In recent years, voice activity detection has been a highly researched field, due to its importance as input stage in many real-world applications. Automated detection of vocalisations in the very first year of life is still a stepchild of this field. On our quest defining acoustic parameters in pre-linguistic vocalisations as markers for neuro(mal)development, we are confronted with the challenge of manually segmenting and annotating hours of variable quality home video material for sequences of infant voice/vocalisations. While in total our corpus comprises video footage of typically developing infants and infants with various neurodevelopmental disorders of more than a year running time, only a small proportion has been processed so far. This calls for automated assistance tools for detecting and/or segmenting infant utterances from real-live video recordings. In this paper, we investigated several approaches of infant voice detection and segmentation, including a rule-based voice activity detector, hidden Markov models with Gaussian mixture observation models, support vector machines, and random forests. Results indicate that the applied methods could be well applied in a semi-automated retrieval of infant utterances from highly non-standardised footage. At the same time, our results show that, a fully automated approach for this problem is yet to come.
|Titel||Interspeech 2016 8-12 Sep 2016, San Francisco|
|Status||Gepubliceerd - 1 jan 2016|
|Evenement||17th Annual Conference of the International Speech Communication Association, INTERSPEECH 2016 - San Francisco, Verenigde Staten van Amerika|
Duur: 8 sep 2016 → 12 sep 2016
|Congres||17th Annual Conference of the International Speech Communication Association, INTERSPEECH 2016|
|Land/Regio||Verenigde Staten van Amerika|
|Periode||8/09/16 → 12/09/16|