Publications de David Imseng | EPFL Graph Search

Feature mapping using far-field microphones for distant speech recognition

Acoustic modeling based on deep architectures has recently gained remarkable success, with substantial improvement of speech recognition accuracy in several automatic speech recognition (ASR) tasks. For distant speech recognition, the multi-channel deep ne ...

2016

Exploiting foreign resources for DNN-based ASR

David Imseng, Petr Motlicek, Philip Neil Garner

Manual transcription of audio databases for the development of automatic speech recognition (ASR) systems is a costly and time-consuming process. In the context of deriving acoustic models adapted to a specific application, or in low-resource scenarios, it ...

2015

Building context-dependent DNN acoustic models using Kullback-Leibler divergence-based state tying

David Imseng

2015

Multilingual speech recognition : a posterior based approach

David Imseng

EPFL2013

Applying Multi- and Cross-Lingual Stochastic Phone Space Transformations to Non-Native Speech Recognition

Hervé Bourlard, Mathew Magimai Doss, Philip Neil Garner, John David Scott Dines, David Imseng

In the context of hybrid HMM/MLP Automatic Speech Recognition (ASR), this paper describes an investigation into a new type of stochastic phone space transformation, which maps "source" phone (or phone HMM state) posterior probabilities (as obtained at the ...

Ieee-Inst Electrical Electronics Engineers Inc2013

The ICSI RT-09 Speaker Diarization System

David Imseng

The speaker diarization system developed at the International Computer Science Institute (ICSI) has played a prominent role in the speaker diarization community, and many researchers in the rich transcription community have adopted methods and techniques d ...

2012

Current trends in multilingual speech processing

Hervé Bourlard, Mathew Magimai Doss, Petr Motlicek, John David Scott Dines, Philip Neil Garner, David Imseng, Hui Liang, Fabio Valente, Lakshmi Babu Saheer

In this paper, we describe recent work at Idiap Research Institute in the domain of multilingual speech processing and provide some insights into emerging challenges for the research community. Multilingual speech processing has been a topic of ongoing int ...

2011

Tuning-Robust Initialization Methods for Speaker Diarization

David Imseng

This paper investigates a typical speaker diarization system regarding its robustness against initialization parameter variation and presents a method to reduce manual tuning of these values significantly. The behavior of an agglomerative hierarchical clus ...

2010