M. Kemal Sönmez

PATHWAY LOGIC: SYMBOLIC ANALYSIS OF BIOLOGICAL SIGNALING

The genomic sequencing of hundreds of organisms including homo sapiens, and the exponential growth in gene expression and proteomic data for many species has revolutionized research in biology. However, the computational analysis of these burgeoning datasets has been hampered by the sparse successes in combinations of data sources, representations, and algorithms. Here we propose the application of symbolic toolsets from the formal methods community to problems of biological interest, particularly signaling pathways, and more specifically mammalian mitogenic and stress responsive pathways. The results of formal symbolic analysis with extremely efficient representations of biological networks provide insights with potential biological impact. In particular, novel hypotheses may be generated which could lead to wet lab validation of new signaling possibilities. We demonstrate the graphic representation of the results of formal analysis of pathways, including navigational abilities, and describe the logical underpinnings of the approach. In summary, we propose and provide an initial description of an algebra and logic of signaling pathways and biologically plausible abstractions that provide the foundation for the application of high-powered tools such as model checkers to problems of biological interest.

Landmark-based speech recognition: report of the 2004 Johns Hopkins summer workshop

Three research prototype speech recognition systems are described, all of which use recently developed methods from artificial intelligence (specifically support vector machines (SVM); dynamic Bayesian networks, and maximum entropy classification) in order to implement, in the form of an ASR, current theories of human speech perception and phonology. All systems begin with a high-D multiframe acoustic-to-distinctive feature transformation, implemented using SVMs trained to detect and classify acoustic phonetic landmarks. Distinctive feature probabilities estimated by the SVMs are then integrated using one of 3 pronunciation models: a dynamic programming algorithm that assumes canonical pronunciation of each word, a dynamic Bayesian network implementation of articulatory phonology, or a discriminative pronunciation model trained using the methods of maximum entropy classification. Log probability scores computed by these models are then combined, using log-linear combination, with other word scores available in the lattice output of a 1st pass recognizer, and the resulting combination score is used to compute a 2nd-pass speech recognition output.

Robustness to telephone handset distortion in speaker recognition by discriminative feature design

Abstract A method is described for designing speaker recognition features that are robust to telephone handset distortion. The approach transforms features such as mel-cepstral features, log spectrum, and prosody-based features with a non-linear artificial neural network. The neural network is discriminatively trained to maximize speaker recognition performance specifically in the setting of telephone handset mismatch between training and testing. The algorithm requires neither stereo recordings of speech during training nor manual labeling of handset types either in training or testing. Results on the 1998 National Institute of Standards and Technology (NIST) Speaker Recognition Evaluation corpus show relative improvements as high as 28% for the new multilayered perceptron (MLP)-based features as compared to a standard mel-cepstral feature set with cepstral mean subtraction (CMS) and handset-dependent normalizing impostor models.

Recent innovations in speech-to-text transcription at SRI-ICSI-UW

We summarize recent progress in automatic speech-to-text transcription at SRI, ICSI, and the University of Washington. The work encompasses all components of speech modeling found in a state-of-the-art recognition system, from acoustic features, to acoustic modeling and adaptation, to language modeling. In the front end, we experimented with nonstandard features, including various measures of voicing, discriminative phone posterior features estimated by multilayer perceptrons, and a novel phone-level macro-averaging for cepstral normalization. Acoustic modeling was improved with combinations of front ends operating at multiple frame rates, as well as by modifications to the standard methods for discriminative Gaussian estimation. We show that acoustic adaptation can be improved by predicting the optimal regression class complexity for a given speaker. Language modeling innovations include the use of a syntax-motivated almost-parsing language model, as well as principled vocabulary-selection techniques. Finally, we address portability issues, such as the use of imperfect training transcripts, and language-specific adjustments required for recognition of Arabic and Mandarin

SRI's 2004 NIST speaker recognition evaluation system

The paper describes our recent efforts in exploring longer-range features and their statistical modeling techniques for speaker recognition. In particular, we describe a system that uses discriminant features from cepstral coefficients, and systems that use discriminant models from word n-grams and syllable-based NERF n-grams. These systems together with a cepstral baseline system are evaluated on the 2004 NIST speaker recognition evaluation dataset. The effect of the development set is measured using two different datasets, one from Switchboard databases and another from the FISHER database. Results show that the difference between the development and evaluation sets affects the performance of the systems only when more training data is available. Results also show that systems using longer-range features combined with the baseline result in about a 31% improvement with 1-side training over the baseline system and about a 61% improvement with 8-side training over the baseline system.

Evolutionary Sequence Modeling for Discovery of Peptide Hormones

We describe a computational framework that models spatial structure along the genomic sequence simultaneously with the temporal evolutionary path structure and show how such models can be used to discover new functional molecules through cross-genomic sequence comparisons. The framework incorporates a priori high-level knowledge of structural and evolutionary constraints in terms of a hierarchical grammar of evolutionary probabilistic models. In particular, we demonstrate a novel computational method for identifying novel prohormones and the processed peptide sites by producing sequence alignments across many species at the functional-element level. We present experimental results with an initial implementation of the algorithm used to identify potential prohormones by comparing the human and mouse proteins, resulting in high accuracy identification in a known set of proteins and a putative novel hormone from an unknown set. Finally, in order to validate the computational methodology, we present the basic molecular biological characterization of the novel putative peptide hormone, including identification in the brain and regional localizations. The success of this approach will have a great impact on our understanding of GPCRs and associated pathways, and help us identify new targets for drug development.

The Contribution of Cepstral and Stylistic Features to SRI's 2005 NIST Speaker Recognition Evaluation System

Recent work in speaker recognition has demonstrated the advantage of modeling stylistic features in addition to traditional cepstral features, but to date there has been little study of the relative contributions of these different feature types to a state-of-the-art system. In this paper we provide such an analysis, based on SRIs submission to the NIST 2005 speaker recognition evaluation. The system consists of 7 subsystems (3 cepstral 4 stylistic). By running independent N-way subsystem combinations for increasing values of N, we fines that (1) a monotonic pattern in the choice of the best N systems allows for the inference of subsystem importance; (2) the ordering of subsystems alternates between cepstral and stylistic; (3) syllable-based prosodic features are the strongest stylistic features, and (4) overall subsystem ordering depends crucially on the amount of training data (1 versus 8 conversation sides). Improvements over the baseline cepstral system, when all systems are combined, range from 47% to 67%, with larger improvements for the 8-side condition. These results provide direct evidence of the complementary contributions of cepstral and stylistic features to speaker discrimination

Multiple Speaker Tracking and Detection

Sonmez, Kemal, Heck, Larry, and Weintraub, Mitchel, Multiple Speaker Tracking and Detection: Handset Normalization and Duration Scoring, Digital Signal Processing10(2000), 133?142.We describe SRIs speaker tracking and detection system in the NIST 1998 Speaker Detection and Tracking Development Evaluation. The system is designed for tracking switchboard conversations and uses a two-speaker and silence hidden Markov model (HMM) with a minimum state duration constraint and Gaussian mixture model (GMM) state distributions adapted from a single gender- and handset-independent imposter model distribution. Speaker tracking is used to segment waveforms for speaker detection, which is carried out by averaging frame scores of the Viterbi path and normalizing for handset variation via a novel parameter interpolation extension of HNORM for use with waveform segments of arbitrary lengths. A short-duration penalty to augment the acoustic scores is also introduced via a nonlinear combination function. Results on the NIST 1998 Speaker Detection and Tracking Development Evaluation dataset are reported.