Recent advances in end-to-end spoken language understanding
This work investigates spoken language understanding (SLU) systems in the scenario when
the semantic information is extracted directly from the speech signal by means of a single …
the semantic information is extracted directly from the speech signal by means of a single …
LIUM SpkDiarization: an open source toolkit for diarization
S Meignier, T Merlin - CMU SPUD Workshop, 2010 - hal.science
This paper presents an open-source diarization toolkit which is mostly dedicated to speaker
and developed by the LIUM. This toolkit includes hierarchical agglomerative clustering …
and developed by the LIUM. This toolkit includes hierarchical agglomerative clustering …
Controlling personality-based stylistic variation with neural natural language generators
Natural language generators for task-oriented dialogue must effectively realize system
dialogue actions and their associated semantics. In many applications, it is also desirable for …
dialogue actions and their associated semantics. In many applications, it is also desirable for …
Investigating adaptation and transfer learning for end-to-end spoken language understanding from speech
This work investigates speaker adaptation and transfer learning for spoken language
understanding (SLU). We focus on the direct extraction of semantic tags from the audio …
understanding (SLU). We focus on the direct extraction of semantic tags from the audio …
End2end acoustic to semantic transduction
In this paper, we propose a novel end-to-end sequence-to-sequence spoken language
understanding model using an attention mechanism. It reliably selects contextual acoustic …
understanding model using an attention mechanism. It reliably selects contextual acoustic …
Equivalence of generative and log-linear models
Conventional speech recognition systems are based on hidden Markov models (HMMs) with
Gaussian mixture models (GHMMs). Discriminative log-linear models are an alternative …
Gaussian mixture models (GHMMs). Discriminative log-linear models are an alternative …
Dialogue history integration into end-to-end signal-to-concept spoken language understanding systems
N Tomashenko, C Raymond… - ICASSP 2020-2020 …, 2020 - ieeexplore.ieee.org
This work investigates the embeddings for representing dialog history in spoken language
understanding (SLU) systems. We focus on the scenario when the semantic information is …
understanding (SLU) systems. We focus on the scenario when the semantic information is …
On building spoken language understanding systems for low resourced languages
A Gupta - arXiv preprint arXiv:2205.12818, 2022 - arxiv.org
Spoken dialog systems are slowly becoming and integral part of the human experience due
to their various advantages over textual interfaces. Spoken language understanding (SLU) …
to their various advantages over textual interfaces. Spoken language understanding (SLU) …
[PDF][PDF] A log-linear discriminative modeling framework for speech recognition
G Heigold - 2010 - www-i6.informatik.rwth-aachen.de
Conventional speech recognition systems are based on Gaussian hidden Markov models
(HMMs). Discriminative techniques such as log-linear modeling have been investigated in …
(HMMs). Discriminative techniques such as log-linear modeling have been investigated in …
Leveraging study of robustness and portability of spoken language understanding systems across languages and domains: the PORTMEDIA corpora
F Lefevre, D Mostefa, L Besacier, Y Esteve… - The International …, 2012 - inria.hal.science
The PORTMEDIA project is intended to develop new corpora for the evaluation of spoken
language understanding systems. The newly collected data are in the field of human …
language understanding systems. The newly collected data are in the field of human …