@article{nemala2012SpeechTech,
<br>abstract = {Humans are quite adept at communicating in presence of noise. However most speech processing systems, like automatic speech and speaker recognition systems, suffer from a significant drop in performance when speech signals are corrupted with unseen background distortions. The proposed work explores the use of a biologically-motivated multi-resolution spectral analysis for speech representation. This approach focuses on the information-rich spectral attributes of speech and presents an intricate yet computationally-efficient analysis of the speech signal by careful choice of model parameters. Further, the approach takes advantage of an information-theoretic analysis of the message and speaker dominant regions in the speech signal, and defines feature representations to address two diverse tasks such as speech and speaker recognition. The proposed analysis surpasses the standard Mel-Frequency Cepstral Coefficients (MFCC), and its enhanced variants (via mean subtraction, variance normalization and time sequence filtering) and yields significant improvements over a state-of-the-art noise robust feature scheme, on both speech and speaker recognition tasks.},
<br>author = {Nemala, Sridhar Krishna and Patil, Kailash and Elhilali, Mounya},
<br>doi = {10.1007/s10772-012-9184-y},
<br>issn = {1381-2416},
<br>journal = {International Journal of Speech Technology},
<br>keywords = {Biomimetic,Multi-resolution,Speaker verification,Speech recognition},
<br>number = {3},
<br>pages = {313--322},
<br>title = {{Recognizing the message and the messenger: biomimetic spectral analysis for robust speech and speaker recognition}},
<br>url = {http://www.ncbi.nlm.nih.gov/pubmed/26412979 http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=PMC4579853 http://link.springer.com/10.1007/s10772-012-9184-y},
<br>volume = {16},
<br>year = {2013}
<br>}