7 search results - page 1 / 2 » Virtual Evidence for Training Speech Recognizers Using Parti... |
NAACL
2007
13 years 6 months ago
2007
Collecting supervised training data for automatic speech recognition (ASR) systems is both time consuming and expensive. In this paper we use the notion of virtual evidence in a g...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
Traditionally, the use of untranscribed speech has been restricted to unsupervised or semi-supervised training of acoustic models. Comparison of recognizers has required labeled d...
NIPS
2007
13 years 6 months ago
2007
We present a new and efficient semi-supervised training method for parameter estimation and feature selection in conditional random fields (CRFs). In real-world applications suc...
CSL
2002
Springer
13 years 4 months ago
2002
Springer
The last decade has witnessed substantial progress in speech recognition technology, with todays state-of-the-art systems being able to transcribe unrestricted broadcast news audi...
CCS
2005
ACM
13 years 10 months ago
2005
ACM
We examine the problem of keyboard acoustic emanations. We present a novel attack taking as input a 10-minute sound recording of a user typing English text using a keyboard, and t...