Important prosody characteristics for spontaneous speech recognition

Kleckova, Jana; Krutisová, Jana; Matoušek, Václav; Schwarz, Jan

doi:10.1109/iconip.2002.1198151

Cited by 2 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, many speech analysis methods (e.g. [4]) are based on linguistics analysis of speaking contents and are subjected to language spoken, while others (e.g. [5]) require sufficient machine learning process beforehand for training their methods with target speakers or certain acoustic conditions, and thus are hardly to be applied to spontaneous conversation in real time.…”

Section: Introductionmentioning

confidence: 99%

A privacy-preserving and language-independent speaking detecting and speaker diarization approach for spontaneous conversation using microphones

Zhang

Yaginuma

2012

2012 IEEE 11th International Conference on Signal Processing

View full text Add to dashboard Cite

Conversation conveys important social signals of human interaction that indicates interest, service-awareness, persuasiveness, etc. In this paper, the authors employ the most common setting of using microphones to capture spontaneous conversation, and introduce a privacy-preserving and languageindependent speech processing approach that can detect speaking and separate speakers in high accuracy for such setting. Experimental results have validated that the approach can deliver accurate speaking recognition results in Japanese, English and Chinese conversation, and can be processed in real time applications.

show abstract

Section: Introductionmentioning

confidence: 99%