• Publications
  • Influence
Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains
  • J. Gauvain, C. Lee
  • Mathematics, Computer Science
  • IEEE Trans. Speech Audio Process.
  • 1 April 1994
TLDR
A framework for maximum a posteriori (MAP) estimation of hidden Markov models (HMM) is presented. Expand
  • 2,461
  • 202
  • PDF
Neural Probabilistic Language Models
TLDR
We propose to fight the curse of dimensionality by learning a distributed representation for words which allows each training sentence to inform the model about an exponential number of semantically neighboring sentences. Expand
  • 523
  • 37
The LIMSI Broadcast News transcription system
TLDR
We describe our development work in moving from laboratory read speech data to real-world or `found' speech data in preparation for the DARPA evaluations on this task from 1996 to 1999. Expand
  • 483
  • 27
Multistage speaker diarization of broadcast news
TLDR
This paper describes recent advances in speaker diarization with a multistage segmentation and clustering system, which incorporates a speaker identification step. Expand
  • 206
  • 21
Lightly supervised and unsupervised acoustic model training
TLDR
The last decade has witnessed substantial progress in speech recognition technology, with today?s state-of-the-art systems being able to transcribe unrestricted broadcast news audio data with a word error of about 20%. Expand
  • 265
  • 19
  • PDF
BREF, a large vocabulary spoken corpus for French
TLDR
This paper presents some of the design considerations of BREF, a large read-speech corpus for French. Expand
  • 234
  • 19
  • PDF
Language recognition using phone latices
TLDR
This paper proposes a new phone lattice based method for automatic language recognition from speech data. Expand
  • 152
  • 18
  • PDF
Speaker adaptation based on MAP estimation of HMM parameters
TLDR
A number of issues related to the application of Bayesian learning techniques to speaker adaptation are investigated. Expand
  • 176
  • 14
Structured Output Layer neural network language model
TLDR
We introduce a new neural network language model (NNLM) based on word clustering to structure the output vocabulary: Structured Output Layer NNLM. Expand
  • 151
  • 9
  • PDF
Where are we in transcribing French broadcast news?
TLDR
This paper describes advances in automatic processing of broadcast news speech in French based on recent improvements to the LIMSI English system. Expand
  • 72
  • 9
  • PDF