Date of Publication :2nd June 2017
Abstract: This paper discuss about detecting speech files in a real world speech recognition task. Detecting files with small background speech or noise, changes the overall behaviour of the Interactive Voice Response System. We experiment with neural networks trained to recognize phonemes, and outline a very simple yet effective approach to discriminate files that contains speech from that of noisy files. We use some popular publically available dataset, to validate our approach
Reference :
-
- Michael L. Seltzer, Dong Yu,Yongqiang Wang, “An Investigation of Deep Neural Networks for Noise Robust Speech Recognition
- Ananya Misra, “ NonSpeech Segmentation in Web Videos”,
- Nima Mesgarani, Samuel Thomas, Hynek Hermansky, “Adaptive Stream Fusion in Multistream Recognition of Speech”
- E. Verteletskaya, K. Sakhnov, “Voice Activity Detection for Speech Enhancement Application”,
- Reinhard Sonnleitner, Bernhard Niedermayer, Gerhard Widmer, Jan Schluter, “A Simple and Effective Spectral Feature for Speech Detection in Mixed Audio Signal”,