#### Filter Results:

- Full text PDF available (64)

#### Publication Year

1959

2016

- This year (0)
- Last five years (13)

#### Publication Type

#### Co-author

#### Publication Venue

#### Key Phrases

Learn More

- John R. Hershey, Peder A. Olsen
- 2007 IEEE International Conference on Acoustics…
- 2007

The Kullback Leibler (KL) divergence is a widely used tool in statistics and pattern recognition. The KL divergence between two Gaussian mixture models (GMMs) is frequently needed in the fields of speech and image recognition. Unfortunately the KL divergence between two GMMs is not analytically tractable, nor does any efficient computational algorithm… (More)

- John R. Hershey, Steven J. Rennie, Peder A. Olsen, Trausti T. Kristjansson
- Computer Speech & Language
- 2010

We present a system that can separate and recognize the simultaneous speech of two people recorded in a single channel. Applied to the monaural speech separation and recognition challenge, the system out-performed all other participants – including human listeners – with an overall recognition error rate of 21.6%, compared to the human error rate of 22.3%.… (More)

- Peder Olsen, Renming Song
- 2005

We consider a system of random walks or directed polymers interacting with an environment which is random in space and time. It was shown by Imbrie and Spencer that in spatial dimensions three or above the behavior is diffusive if the directed polymer interacts weakly with the environment and if the random environment follows the Bernoulli distribution.… (More)

- Trausti T. Kristjansson, John R. Hershey, Peder A. Olsen, Steven J. Rennie, Ramesh A. Gopinath
- INTERSPEECH
- 2006

We describe a system for model based speech separation which achieves superhuman recognition performance when two talkers speak at similar levels. The system can separate the speech of two speakers from a single channel recording with remarkable results. It incorporates a novel method for performing two-talker speaker identification and gain estimation. We… (More)

- Peder A. Olsen, Ramesh A. Gopinath
- IEEE Transactions on Speech and Audio Processing
- 2002

This paper proposes a new covariance modeling technique for Gaussian mixture models. Specifically the inverse covariance (precision) matrix of each Gaussian is expanded in a rank-1 basis i.e., /spl Sigma//sub j//sup -1/=P/sub j/=/spl Sigma//sub k=1//sup D//spl lambda//sub k//sup j/a/sub k/a/sub k//sup T/, /spl lambda//sub k//sup j//spl isin//spl Ropf/,a/sub… (More)

- Steven J. Rennie, John R. Hershey, Peder A. Olsen
- IEEE Signal Processing Magazine
- 2010

We have described some of the problems with modeling mixed acoustic signals in the log spectral domain using graphical models, as well as some current approaches to handling these problems for multitalker speech separation and recognition. We have also reviewed methods for inference on FHMMs (factorial hidden Markov model) and methods for handling the… (More)

- Cho-Jui Hsieh, Peder A. Olsen
- ICML
- 2014

We describe a novel approach to optimizing matrix problems involving nuclear norm regulariza-tion and apply it to the matrix completion problem. We combine methods from non-smooth and smooth optimization. At each step we use the proximal gradient to select an active sub-space. We then find a smooth, convex relaxation of the smaller subspace problems and… (More)

- Scott Axelrod, Ramesh A. Gopinath, Peder A. Olsen
- INTERSPEECH
- 2002

We consider a family of Gaussian mixture models for use in HMM based speech recognition system. These " SPAM " models have state independent choices of subspaces to which the precision (inverse covariance) matrices and means are restricted to belong. They provide a flexible tool for robust, compact, and fast acoustic modeling. The focus of this paper is on… (More)

- Scott Axelrod, Vaibhava Goel, Ramesh A. Gopinath, Peder A. Olsen, Karthik Visweswariah
- IEEE Transactions on Speech and Audio Processing
- 2005

A standard approach to automatic speech recognition uses hidden Markov models whose state dependent distributions are Gaussian mixture models. Each Gaussian can be viewed as an exponential model whose features are linear and quadratic monomials in the acoustic vector. We consider here models in which the weight vectors of these exponential models are… (More)

- Scott Axelrod, Vaibhava Goel, Ramesh A. Gopinath, Peder A. Olsen, Karthik Visweswariah
- IEEE Transactions on Audio, Speech, and Language…
- 2007

In this paper, we study discriminative training of acoustic models for speech recognition under two criteria: maximum mutual information (MMI) and a novel "error-weighted" training technique. We present a proof that the standard MMI training technique is valid for a very general class of acoustic models with any kind of parameter tying. We report… (More)