Add to ORKGWe present an efficient discriminative training procedure utilizing phone lattices. Different approaches to expediting lattice generation, statistics collection, and convergence were studied. We also propose a new discriminative training criterion, namely, minimum phone frame error (MPFE). When combined with the maximum mutual information (MMI) criterion using I-smoothing, replacing the standard minimum phone error (MPE) criterion with MPFE led to a small but consistent win in several applications. Phone-lattice-based discriminative training gave around 8 % to 12 % relative word error rate (WER) reduction in SRI’s latest English Conversational Telephone Speech and Broadcast News transcription systems developed for DARPA’s EARS project. 1
The linguistic content of a speech signal is a source of unwanted variation which can degrade speake...
Discriminative training schemes, such as Maximum Mutual Information Estimation (MMIE), have been us...
Lattice segmentation techniques developed for Minimum Bayes Risk decoding in large vocabulary speech...
In this paper we introduce the Minimum Phone Error (MPE) and Minimum Word Error (MWE) criteria for t...
This paper addresses the use of discriminative training criteria for Speaker Adaptive Training (SAT)...
This paper proposes a new phone lattice based method for automatic language recognition from speech ...
[[abstract]]This paper describes a discriminative-based training approach to continuous phone recogn...
This paper describes a lattice-based framework for maximum mutual information estimation (MMIE) of H...
Previously, we proposed a flexible two-layered speech recogniser architecture, called FLaVoR. In the...
In discriminative training, such as Maximum Mutual Information Estimation (MMIE) training, a word la...
Discriminative training has become an important means for estimating model parameters in many statis...
The current “state-of-the-art ” in phonetic speaker recognition uses relative frequencies of phone n...
In this paper, we present a general algorithmic framework based on WFSTs for implementing a variety ...
Abstract. The Minimum Phone Error (MPE) criterion for discriminative training was shown to be able t...
Discriminative training schemes, such as Maximum Mutual Infor-mation Estimation (MMIE), have been us...
The linguistic content of a speech signal is a source of unwanted variation which can degrade speake...
Discriminative training schemes, such as Maximum Mutual Information Estimation (MMIE), have been us...
Lattice segmentation techniques developed for Minimum Bayes Risk decoding in large vocabulary speech...
In this paper we introduce the Minimum Phone Error (MPE) and Minimum Word Error (MWE) criteria for t...
This paper addresses the use of discriminative training criteria for Speaker Adaptive Training (SAT)...
This paper proposes a new phone lattice based method for automatic language recognition from speech ...
[[abstract]]This paper describes a discriminative-based training approach to continuous phone recogn...
This paper describes a lattice-based framework for maximum mutual information estimation (MMIE) of H...
Previously, we proposed a flexible two-layered speech recogniser architecture, called FLaVoR. In the...
In discriminative training, such as Maximum Mutual Information Estimation (MMIE) training, a word la...
Discriminative training has become an important means for estimating model parameters in many statis...
The current “state-of-the-art ” in phonetic speaker recognition uses relative frequencies of phone n...
In this paper, we present a general algorithmic framework based on WFSTs for implementing a variety ...
Abstract. The Minimum Phone Error (MPE) criterion for discriminative training was shown to be able t...
Discriminative training schemes, such as Maximum Mutual Infor-mation Estimation (MMIE), have been us...
The linguistic content of a speech signal is a source of unwanted variation which can degrade speake...
Discriminative training schemes, such as Maximum Mutual Information Estimation (MMIE), have been us...
Lattice segmentation techniques developed for Minimum Bayes Risk decoding in large vocabulary speech...