Role of Linear, Mel and Inverse-Mel Filterbanks in Automatic Recognition of Speech from High-Pitched Speakers
- 26 February 2019
- journal article
- research article
- Published by Springer Nature in Circuits, Systems, and Signal Processing
- Vol. 38 (10) , 4667-4682
Abstract
No abstract availableKeywords
This publication has 31 references indexed in Scilit:
- Pitch-Adaptive Front-End Features for Robust Children’s ASR2016
- Deep-neural network approaches for speech recognition with heterogeneous groups of speakers including childrenNatural Language Engineering, 2016
- Enhancing the recognition of children's speech on acoustically mismatched ASR system2015
- Vocal tract length normalisation approaches to DNN-based children's and adults' speech recognition2014
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012
- Linear versus mel frequency cepstral coefficients for speaker recognition2011
- Technical foundations of TANDEM-STRAIGHT, a speech analysis, modification and synthesis frameworkSādhanā, 2011
- Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech RecognitionIEEE Transactions on Audio, Speech, and Language Processing, 2011
- Restructuring speech representations using a pitch-adaptive time–frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in soundsSpeech Communication, 1999
- Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentencesIEEE Transactions on Acoustics, Speech, and Signal Processing, 1980