Sciweavers

ICASSP
2008
IEEE
14 years 6 months ago
HMM adaptation using a phase-sensitive acoustic distortion model for environment-robust speech recognition
In this paper, we present a new approach to HMM adaptation that jointly compensates for additive and convolutive acoustic distortion in environment-robust speech recognition. The ...
Jinyu Li, Li Deng, Dong Yu, Yifan Gong, Alex Acero
ICASSP
2008
IEEE
14 years 6 months ago
Combining open vocabulary recognition and word confusion networks
A limitation of most speech recognizers is that they only recognize words from a fixed vocabulary. In this paper, we explore a technique for addressing this deficiency using aut...
Keith Vertanen
ICASSP
2008
IEEE
14 years 6 months ago
Rhetorical-State Hidden Markov Models for extractive speech summarization
We propose an extractive summarization system with a novel non-generative probabilistic framework for speech summarization. One of the most underutilized features in extractive su...
Pascale Fung, Ricky Ho Yin Chan, Justin Jian Zhang
ICASSP
2008
IEEE
14 years 6 months ago
Information theoretic bounds on neural prosthesis effectiveness: The importance of spike sorting
We compute the capacity of neural prostheses using a vector Poisson process model for the neural population channel. For single-electrode stimulation prostheses, the capacity is p...
Ilan N. Goodman, Don H. Johnson
ICASSP
2008
IEEE
14 years 6 months ago
Unsupervised optimal phoneme segmentation: Objectives, algorithm and comparisons
Phoneme segmentation is a fundamental problem in many speech recognition and synthesis studies. Unsupervised phoneme segmentation assumes no knowledge on linguistic contents and a...
Yu Qiao, Naoya Shimomura, Nobuaki Minematsu
ICASSP
2008
IEEE
14 years 6 months ago
Extracting question/answer pairs in multi-party meetings
Understanding multi-party meetings involves tasks such as dialog act segmentation and tagging, action item extraction, and summarization. In this paper we introduce a new task for...
Andreas Kathol, Gökhan Tür
ICASSP
2008
IEEE
14 years 6 months ago
Statistical approach to vocal tract transfer function estimation based on factor analyzed trajectory HMM
In this paper, we describe a novel statistical approach to the vocal tract transfer function (VTTF) estimation of a speech signal based on a factor analyzed trajectory hidden Mark...
Tomoki Toda, Keiichi Tokuda
ICASSP
2008
IEEE
14 years 6 months ago
Modulation decompositions for the interpolation of long gaps in acoustic signals
This paper presents a modulation-based reconstruction method for audio signals across long gaps of missing samples. We use LTI filterbanks followed by a multiplicative model that...
Pascal Clark, Les E. Atlas
ICASSP
2008
IEEE
14 years 6 months ago
Speech denoising using nonnegative matrix factorization with priors
We present a technique for denoising speech using nonnegative matrix factorization (NMF) in combination with statistical speech and noise models. We compare our new technique to s...
Kevin W. Wilson, Bhiksha Raj, Paris Smaragdis, Aja...
ICASSP
2008
IEEE
14 years 6 months ago
Accurate statistical spoken language understanding from limited development resources
Robust Spoken Language Understanding (SLU) is a key component of spoken dialogue systems. Recent statistical approaches to this problem require additional resources (e.g. gazettee...
I. V. Meza-Ruiz, Sebastian Riedel, Oliver Lemon