ACL
2010
13 years 2 months ago
2010
In recent years, research in natural language processing has increasingly focused on normalizing SMS messages. Different well-defined approaches have been proposed, but the proble...
TASLP
2002
13 years 4 months ago
2002
Abstract--This paper explores packet loss recovery for automatic speech recognition (ASR) in spoken dialog systems, assuming an architecture in which a lightweight client communica...
SPEECH
2002
13 years 4 months ago
2002
Automatic speech recognition of real-live broadcast news (BN) data (Hub-4) has become a challenging research topic in recent years. This paper summarizes our key efforts to build ...
TASLP
2008
13 years 4 months ago
2008
In this paper we investigate the combination of complementary acoustic feature streams in large vocabulary continuous speech recognition (LVCSR). We have explored the use of acoust...
TASLP
2008
13 years 4 months ago
2008
Abstract-- Speaker space based adaptation methods for automatic speech recognition have been shown to provide significant performance improvements for tasks where only a few second...
ICPR
2010
IEEE
13 years 4 months ago
2010
IEEE
Abstract—Whole-book recognition is a document image analysis strategy that operates on the complete set of a book’s page images using automatic adaptation to improve accuracy. ...
ICASSP
2010
IEEE
13 years 5 months ago
2010
IEEE
In this paper we describe a method for Minimum Bayes Risk decoding for speech recognition. This is a technique similar to Consensus a.k.a. Confusion Network Decoding, in which we ...
NAACL
1994
13 years 6 months ago
1994
We desert'be our latest attempt at adaptive language modeling. At the heart of our approachis a Maximum Entropy(ME) modelwhich inc.orlxnatesmanyknowledgesources in a consiste...
TREC
2000
13 years 6 months ago
2000
This paper presents work done at Cambridge University for the TREC-9 Spoken Document Retrieval (SDR) track. The CUHTK transcriptions from TREC-8 with Word Error Rate (WER) of 20.5...
ANLP
2000
13 years 6 months ago
2000
In this paper, we analyze the performance of name finding in the context of a variety of automatic speech recognition (ASR) systems and in the context of one optical character rec...