Deep neural networks (DNNs), which are extensions of artificial neural networks, can learn
higher levels of feature hierarchy established by lower level features by transforming the raw …

Title description The C-ORAL-ROM book and DVD provide a unique set of comparable
corpora of spontaneous speech for the main Romance languages, French, Italian …

We propose a new framework for joint multichannel speech source separation and acoustic
noise reduction. In this framework, we start by formulating the minimum-mean-square error …

This dissertation proposes a model of phonological relationships, the Probabilistic
Phonological Relationship Model (PPRM), that quantifies how predictably distributed two …

This paper presents our real-time meeting analyzer for monitoring conversations in an
ongoing group meeting. The goal of the system is to recognize automatically “who is …

State-of-the-art automatic speech recognition (ASR) system development is data and
computation intensive. The optimal design of deep neural networks (DNNs) for these …

We present novel neural network based language models that can correct automatic speech
recognition (ASR) errors by using speech recognizer output as a context. These models …

This paper addresses a front-end system for speech recognition of spontaneous
conversational speech signals that are recorded with asynchronous distributed microphones …

Here we propose online adaptive beamforming for automatic speech recognition (ASR) in
meetings in noisy, reverberant environments. The proposed method is based on recently …

This paper addresses a minimum variance distortionless response (MVDR) beamforming
based speech enhancement approach for meeting speech recognition. In a meeting …