Learn More
In this work we formulate a novel approach to estimating the parameters of continuous density HMMs for speaker-independent (SI) continuous speech recognition. It is motivated by the fact that variability in SI acoustic models is attributed to both phonetic variation and variation among the speakers of the training population, that is independent of the(More)
In the early 1990s, the availability of the TIMIT read-speech phonetically transcribed corpus led to work at AT&T on the automatic inference of pronunciation variation. This work, brie¯y summarized here, used stochastic decision trees trained on phonetic and linguistic features, and was applied to the DARPA North American Business News read-speech ASR task.(More)
An 835 base pair (bp) fragment of mitochondrial DNA (mtDNA) was sequenced to characterize genetic variation within and among 1,053 samples comprising five regional populations each of longtail macaques (Macaca fascicularis) and rhesus macaques (Macaca mulatta), and one sample each of Japanese (M. fuscata) and Taiwanese (M. cyclopis) macaques. The mtDNA(More)
This paper describes the speaker adaptive training (SAT) approach for speaker independent (SI) speech recognizers as a method for joint speaker normalization and estimation of the parameters of the SI acoustic models. In SAT, speaker characteristics are mod-eled explicitly as linear transformations of the SI acoustic parameters. The effect of inter-speaker(More)
In this work, we propose an algorithm for acoustic source localization based on time delay of arrival (TDOA) estimation. In earlier work by other authors, an initial closed-form approximation was first used to estimate the true position of the speaker followed by a Kalman filtering stage to smooth the time series of estimates. In the proposed algorithm,(More)
In this paper, we consider an acoustic beamforming application where two speakers are simultaneously active. We construct one subband-domain beamformer in generalized sidelobe canceller (GSC) configuration for each source. In contrast to normal practice, we then jointly optimize the active weight vectors of both GSCs to obtain two output signals with(More)
In recent work, we proposed the rational all-pass transform (RAPT) as the basis of a speaker adaptation scheme intended for use with a large vocabulary speech recognition system. It was shown that RAPT-based adaptation reduces to a linear transformation of cepstral means, much like the better known maximum likelihood linear regression (MLLR). In a set of(More)
In this work, we present our progress in multi-source far field automatic speech-to-text transcription for lecture speech. In particular, we show how the best of several far field channels can be selected based on a signal-to-noise ratio criterion, and how the signals from multiple channels can be combined at either the waveform level using blind channel(More)
Mitochondrial and Y-chromosome DNA were analyzed from 10,300-year-old human remains excavated from On Your Knees Cave on Prince of Wales Island, Alaska (Site 49-PET-408). This individual's mitochondrial DNA (mtDNA) represents the founder haplotype of an additional subhaplogroup of haplogroup D that was brought to the Americas, demonstrating that widely held(More)