Recently, we have shown that context-dependent deep neural network hidden Markov models (CD-DNN-HMMs) can achieve very promising recognition results on large vocabulary speech recognition tasks, as evidenced by over one third fewer word errors than the discriminatively trained conventional HMM-based systems on the 300hr Switchboard benchmark task. In this paper, we propose and describe two type...

Automatic speech recognition (ASR) systems typically have a static dictionary of word pronunciations for matching acoustic models to words. In this work, we argue that, in fact, pronunciations in spontaneous speech are dynamic and that ASR systems should change models in accordance with contextual factors. Two variables, speaking rate and word frequency, should be particularly promising for det...

In this paper, we present two efficient strategies for likelihood computation and decoding in a continuous speech recognizer using an underlying nonlinear state-space dynamic model for the hidden speech dynamics. The state-space model has been specially constructed so as to be suitable for the conversational or casual style of speech where phonetic reduction abounds. Two specific decoding algor...

This article proposes a mechanism for improving the collaboration in a distributed virtual environment with heterogeneous networking, adapting the operation of the virtual environment, to the varying conditions of the network. Normally, a user who participates in a virtual environment with other users, does not have to his disposition the ideal network conditions for the transmission and recept...

Action checklist 1. Meet and discuss with colleagues, nurses and resuscitation trainers. Nurses are most important as they are the staff who make the most of these calls. 2. Use the attached 2222 PowerPoint presentation at meetings if you wish. 3. Discuss with patients groups / representatives if available 4. Discuss with / Send letter to Hospital Medical Director / Management (see Draft letter...

Not all the questions related to the semi-supervised training of hybrid ASR system with DNN acoustic model were already deeply investigated. In this paper, we focus on the question of the granularity of confidences (per-sentence, per-word, perframe), the question of how the data should be used (dataselection by masks, or in mini-batch SGD with confidences as weights). Then, we propose to re-tun...

Dialogue Act recognition associate dialogue acts (i.e., semantic labels) to utterances in a conversation. The problem of associating semantic labels to utterances can be treated as a sequence labeling problem. In this work, we build a hierarchical recurrent neural network using bidirectional LSTM as a base unit and the conditional random field (CRF) as the top layer to classify each utterance i...

In this paper we describe a new testbed for developing speech recognition algorithms a VoiceMail transcription task, analogous to other tasks such as the Switchboard, CallHome [1] and the Hub 4 tasks [2] which are currently used by speech recognition researchers. Spontaneous speech occurring in day-today life can broadly be classi ed into two categories (i) where the speaker does not receive an...