Richard M. Stern

Prof. Richard M. Stern

orcid

Research Focus & Metrics

Academic Career Length

49Years (1978-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 1990 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
DCD.A. Coast
D.A. Coast
Richard M. SternRichard M. Stern
Richard M. Stern
GCG.G. Cano
G.G. Cano
SBS.A. Briller
S.A. Briller
This paper describes a new approach to ECG arrhythmia analysis based on "hidden Markov modeling" (HMM), a technique successfully used since the mid-1970's to model speech waveforms for automatic speech recognition. Many ventricular arrhythmias can be classified by detecting and analyzing QRS complexes and determining R-R intervals. Classification of supraventricular arrhythmias, however, often requires detection of the P wave in addition to the QRS complex. The hidden Markov modeling approach combines structural and statistical knowledge of the ECG signal in a single parametric model. Model parameters are estimated from training data using an iterative, maximum likelihood reestimation algorithm. Initial results suggest that this approach may provide improved supraventricular arrhythmia analysis through accurate representation of the entire beat including the P wave.

23 March 2016 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Open access
CKChanwoo Kim
Chanwoo Kim
Richard M. SternRichard M. Stern
Richard M. Stern
This paper presents a new feature extraction algorithm called power normalized Cepstral coefficients (PNCC) that is motivated by auditory processing. Major new features of PNCC processing include the use of a power-law nonlinearity that replaces the traditional log nonlinearity used in MFCC coefficients, a noise-suppression algorithm based on asymmetric filtering that suppresses background excitation, and a module that accomplishes temporal masking. We also propose the use of medium-time power analysis in which environmental parameters are estimated over a longer duration than is commonly used for speech, as well as frequency smoothing. Experimental results demonstrate that PNCC processing provides substantial improvements in recognition accuracy compared to MFCC and PLP processing for speech in the presence of various types of additive noise and in reverberant environments, with only slightly greater computational cost than conventional MFCC processing, and without degrading the recognition accuracy that is observed while training and testing using clean speech. PNCC processing also provides better recognition accuracy in noisy environments than techniques such as vector Taylor series (VTS) and the ETSI advanced front end (AFE) while requiring much less computation. We describe an implementation of PNCC using “online processing” that does not require future knowledge of the input.

24 December 2002
Verified
Conference Paper
Closed access
PMP.J. Moreno
P.J. Moreno
BRB. Raj
B. Raj
Richard M. SternRichard M. Stern
Richard M. Stern

26 September 2005 in IEEE Signal Processing Magazine
Verified
Journal Article
Closed access
BRB. Raj
B. Raj
Richard M. SternRichard M. Stern
Richard M. Stern
In this article we have reviewed a wide variety of techniques based on the identification of missing spectral features that have proved effective in reducing the error rates of automatic speech recognition systems. These approaches have been conspicuously effective in ameliorating the effects of transient maskers such as impulsive noise or background music. We described two broad classes of missing feature algorithms: feature-vector imputation algorithms (which restore unreliable components of incoming feature vectors) and classifier-modification algorithms (which dynamically reconfigure the classifier itself to cope with the effects of unreliable feature components). We reviewed the mathematics of four major missing feature techniques: the feature-imputation techniques of cluster-based reconstruction and covariance-based reconstruction, and the classifier-modification methods of class-conditional imputation and marginalization. We also discussed the ways in which the common feature extraction procedures of cepstral analysis, temporal-difference features, and mean subtraction can be handled by speech recognition systems that make use of missing feature techniques. We concluded with a discussion of a small number of selected experimental results. These results confirm the effectiveness of all types of missing feature approaches discussed in ameliorating the effects of both stationary and transient noise, as well as the particular effectiveness of both soft masks and fragment decoding.

1 September 2004 in Speech Communication
Verified
Journal Article
Closed access
BRBhiksha Raj
Bhiksha Raj
MSMichael L. Seltzer
Michael L. Seltzer
Richard M. SternRichard M. Stern
Richard M. Stern

1 July 1978 in The Journal of the Acoustical Society of America
Verified
Journal Article
Closed access
Richard M. SternRichard M. Stern
Richard M. Stern
HCH. Steven Colburn
H. Steven Colburn
A model for the subjective lateral position of 500‐Hz tones is presented and compared with experimental lateralization data. Previous papers in this series have explicitly described the auditory‐nerve response to these stimuli and proposed a binaural displayer that interaurally compares the auditory‐nerve firing times. The outputs of the displayer are postulated to represent the only information about detailed firing times that is available to the brain. In the present paper, lateral‐position predictions are obtained by a central nonoptimal weighting of these outputs that depends on the interaural intensity difference of the tone. These predictions describe the results of lateralization‐matching experiments more accurately and over a wider range of stimulus conditions than previous theories, except for those results which suggest that low‐frequency binauraltones can generate multiple perceptual images. The predictions of our model are also consistent with the results of centering and laterality‐comparison experiments. It is argued that the data discussed in this paper are generally incompatible with theories that propose a peripheral interaction of interaural timing and intensity information such as the latency hypothesis.