European speech databases for telephone applications

Höge, Harald; Tropf, Herbert S.; Winski, Richard; Heuvel, H. van den; Haeb‐Umbach, Reinhold; Choukri, Khalid

doi:10.1109/icassp.1997.598873

Cited by 25 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed decoding strategy was implemented in the prototype Synface real-time decoder. Initial experiments [7] were carried out on the Swedish SpeechDat telephone database [8,9] with the purpose of evaluating phone recognition accuracy with different levels of hypothesis look-ahead. Offline, tests were conducted, using HTK [10] on the same task, as a baseline.…”

Section: Resultsmentioning

confidence: 99%

Low-latency incremental speech transcription in the synface project

Seward¹

2003

8th European Conference on Speech Communication and Technology (Eurospeech 2003)

View full text Add to dashboard Cite

In this paper, a real-time decoder for low-latency online speech transcription is presented. The system was developed within the Synface project, which aims to improve the possibilities for hard of hearing people to use conventional telephony by providing speech-synchronized multimodal feedback. This paper addresses the specific issues related to HMM-based incremental phone classification with real-time constraints. The decoding algorithm described in this work enables a trade-off to be made between improved recognition accuracy and reduced latency. By accepting a longer latency per output increment, more time can be ascribed to hypothesis look-ahead and by that improve classification accuracy. Experiments performed on the Swedish SpeechDat database show that it is possible to generate the same classification as is produced by non-incremental decoding using HTK, by adopting a latency of approx. 150 ms or more.

show abstract

Section: Resultsmentioning

confidence: 99%

Low-latency incremental speech transcription in the synface project

Seward¹

2003

8th European Conference on Speech Communication and Technology (Eurospeech 2003)

View full text Add to dashboard Cite

show abstract

“…As a proof of concept, we ran experiments on a sub-set of the SpeechDat Portuguese corpus [16]. We selected 27 different keywords, shown in Table 1, from the SpeechDat application words list.…”

Section: Experiments Using Dtwmentioning

confidence: 99%

Privacy-preserving Query-by-Example Speech Search

Portêlo

Abad

Raj

et al. 2015

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

This paper investigates a new privacy-preserving paradigm for the task of Query-by-Example Speech Search using Secure Binary Embeddings, a hashing method that converts vector data to bit strings through a combination of random projections followed by banded quantization. The proposed method allows performing spoken query search in an encrypted domain, by analyzing ciphered information computed from the original recordings. Unlike other hashing techniques, the embeddings allow the computation of the distance between vectors that are close enough, but are not perfect matches. This paper shows how these hashes can be combined with Dynamic Time Warping based on posterior derived features to perform secure speech search. Experiments performed on a sub-set of the SpeechDat Portuguese corpus showed that the proposed privacy-preserving system obtains similar results to its non-private counterpart.

show abstract

“…The relevance of validation of large SLRs emerged when the SpeechDat project (Höge et al 1997) was started around 1995. The SLRs within this project were produced in a European framework according to design and recording specifications similar to the American-English Macrophone corpus (Bernstein et al 1994) and the Dutch Polyphone corpus (Den Os et al 1995).…”

Section: Introductionmentioning

confidence: 99%

Validation of spoken language resources: an overview of basic aspects

Heuvel

Iskra²,

Sanders

et al. 2007

Lang Resources & Evaluation

View full text Add to dashboard Cite

Spoken language resources (SLRs) are essential for both research and application development. In this article we clarify the concept of SLR validation. We define validation and how it differs from evaluation. Further, relevant principles of SLR validation are outlined. We argue that the best way to validate SLRs is to implement validation throughout SLR production and have it carried out by an external and experienced institute. We address which tasks should be carried out by the validation institute, and which not. Further, we list the basic issues that validation criteria for SLR should address. A standard validation protocol is shown, illustrating how validation can prove its value throughout the production phase in terms of pre-validation, full validation and pre-release validation.

show abstract

European speech databases for telephone applications

Cited by 25 publications

References 4 publications

Low-latency incremental speech transcription in the synface project

Low-latency incremental speech transcription in the synface project

Privacy-preserving Query-by-Example Speech Search

Validation of spoken language resources: an overview of basic aspects

Contact Info

Product

Resources

About