Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Se

By S. Davis, P. Mermelstein. 1980

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Speech & Audio

Citations in the corpus

Librispeech: An ASR corpus based on public domain audio books (2015, methodology): “For this first decoding pass we use a triphone model discriminatively trained with Boosted MMI [12], based on MFCC [13] features processed with frame-splicing over 7 frames, followed by LDA, followed by a global semi-tied covariance (STC) transform [14] .”
Parallel training of Deep Neural Networks with Natural Gradient and Parameter Averaging (2014, methodology): “[31] Steven Davis and Paul Mermelstein, “Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences,” Acoustics, Speech and Signal Processing, IEEE Transactions on, vol.”
A review of biometric technology along with trends and prospects (2014, background): “Table 4: Summary of behavioral modalities: Modality Feature Set Recognition Techniques Datasets Voice Spectrum, Glottal pulse features, pitch, energy, duration, rhythm, temporal features, phones, idiolects, semantics, accent, pronunciation, LPCC [204], MFCC [205], VQ [206-208], HMM [209], GMM [210, ”
AudioCaps: Generating Captions for Audios in The Wild (2019, methodology): “MFCC-LSTM does not perform as well as VGGish-LSTM , even with the similar convolutional recurrent encoder.”
Privacy-Preserving Machine Learning for Speech Processing (2012, methodology): “The most commonly used parametrization for speech is Mel Frequency Cepstral Coefficients (MFCC) [Davis and Mermelstein, 1980].”
A comparison of features for synthetic speech detection (2015, methodology): “In MFCC, the filters are placed in mel scale, having denser spacing in t he low-frequency region [21].”
Histogram equalization of speech representation for robust speech recognition (2005, methodology): “energy coecient, 14 MFCC coecients [ 33 ] and the 1st and 2nd regression coecients”
Sphinx-4: a flexible open source framework for speech recognition (2004, background): “For example, Sphinx-4 is typically configured with a FrontEnd (see Section IV) that produces Mel-Frequency Cepstral Coefficients (MFCCs) [ 15 ].”
Automatic large-scale classification of bird sounds is strongly improved by unsupervised feature learning (2014, methodology): “A convention, originating from speech processing, is to transform the Mel spectrum using a cepstral analysis and then to keep the lower coefficients (e.g., the first 13) which typically contain most of the energy (Davis & Mermelstein, 1980).”
Multi-view clustering via canonical correlation analysis (2009, methodology): “The audio features are standard 12-dimensional mel cepstra ( Davis & Mermelstein, 1980 ) and their derivatives and double derivatives computed every 10ms over a 20ms window, and nally concatenated over a window of 440ms centered on the current frame, for a total of 1584 dimensions.”