Introduction to the IST-HLT project speech-driven multimodal automatic directory assistance (SMADA)

Bécht, F.; Os, E.A. den; Boves, L.W.J.; Sienel, Juergen

doi:10.21437/icslp.2000-373

Cited by 4 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our experiment we have seen little positive effect of training a complete set of sub-word models on speech recorded in the application. In [3] it is shown that inclusion of a small number of application specific sub-word units does improve perform ance on a city name recognition task. Including an even smaller number of whole word models for the largest cities improves performance even further.…”

Section: Resultsmentioning

confidence: 99%

Impact of speaking style and speaking task on acoustic models

Sturm¹,

Kamperman²,

Boves³

et al. 2000

6th International Conference on Spoken Language Processing (ICSLP 2000)

Self Cite

View full text Add to dashboard Cite

The loss in performance caused by mismatch between train and test material suggests a need for task specific acoustic models, especially for highly demanding tasks. However, since the training of these models is extremely expensive, general pur pose models are more attractive. In this paper we address the impact of mismatch in speaking style and task. We trained three sets of acoustic models on data from different tasks, involving both read and extemporaneous speech. The average utterance length in the training corpora varied between 10.5 and 1.2 words. The models were tested on matched as well on very dif ferent tasks. The results suggest that general purpose models trained from short utterances are to be preferred in most spoken dialog systems. However, these models might not perform ade quately in dictation tasks.

show abstract

Section: Resultsmentioning

confidence: 99%

Impact of speaking style and speaking task on acoustic models

Sturm¹,

Kamperman²,

Boves³

et al. 2000

6th International Conference on Spoken Language Processing (ICSLP 2000)

Self Cite

View full text Add to dashboard Cite

show abstract

Voice Search

Wang

et al. 2011

Spoken Language Understanding

View full text Add to dashboard Cite

Dynamic scheduling of decoding processes for directory assistance

Mori

Béchet

Subsol

et al.

2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).

View full text Add to dashboard Cite

This paper deals with the difficult task of recognition of a large vocabulary of proper names in a directory assistance application. Research on the European project SMADA has shown that there is a need of an elaborate and effective decision strategy that limits the risk of false automation. This paper proposes a new strategy which integrates, as well as a general decoder, a set of decoders specialized in some specific situations. Specialized recognition processes do not need to be applicable for every input, but they have to be scheduled and performed only under certain conditions. A first implementation of such a model is proposed here, through a rejection strategy of the hypotheses output by a general decoder. This strategy leads to a very significant improvement over the results obtained by a standard rejection method based on acoustic confidence scores only.

show abstract

Introduction to the IST-HLT project speech-driven multimodal automatic directory assistance (SMADA)

Abstract: The following full text is an author's version which may differ from the publisher's version.For additional information about this publication click this link. http://hdl.handle.net/2066/75039Please be advised that this information was generated on 2022-08-08 and may be subject to change.

Cited by 4 publications

References 0 publications

Impact of speaking style and speaking task on acoustic models

Impact of speaking style and speaking task on acoustic models

Voice Search

Dynamic scheduling of decoding processes for directory assistance

Contact Info

Product

Resources

About