The DARPA 1000-word resource management database for continuous speech recognition

Price, Patti; Fisher, William M.; Bernstein, Jared; Pallett, David S.

doi:10.1109/icassp.1988.196669

Cited by 239 publications

(93 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The second dataset, RM-3000 [32], consists of 3000 sentences spoken by a single native English speaking male speaker. The sentences were randomly selected from the 8000 sentences in the Resource Management (RM) Corpus [33]. The vocabulary size of 1000 words and no strict grammar give a more realistic environment, and more challenging task when compared to GRID.…”

Section: Resultsmentioning

confidence: 99%

A Comparison of Perceptually Motivated Loss Functions for Binary Mask Estimation in Speech Separation

Websdale¹,

Milner²

2017

Interspeech 2017

View full text Add to dashboard Cite

This work proposes and compares perceptually motivated loss functions for deep learning based binary mask estimation for speech separation. Previous loss functions have focused on maximising classification accuracy of mask estimation but we now propose loss functions that aim to maximise the hit minus false-alarm (HIT-FA) rate which is known to correlate more closely to speech intelligibility. The baseline loss function is binary cross-entropy (CE), a standard loss function used in binary mask estimation, which maximises classification accuracy. We propose first a loss function that maximises the HIT-FA rate instead of classification accuracy. We then propose a second loss function that is a hybrid between CE and HIT-FA, providing a balance between classification accuracy and HIT-FA rate. Evaluations of the perceptually motivated loss functions with the GRID database show improvements to HIT-FA rate and ESTOI across babble and factory noises. Further tests then explore application of the perceptually motivated loss functions to a larger vocabulary dataset.

show abstract

Section: Resultsmentioning

confidence: 99%

A Comparison of Perceptually Motivated Loss Functions for Binary Mask Estimation in Speech Separation

Websdale¹,

Milner²

2017

Interspeech 2017

View full text Add to dashboard Cite

show abstract

“…The initial work developing and implementing the above described stack decoder was performed using the Resource Management (RM) database [18]. The WSJ-pilot database training and development-test data has only been fully available for about 5 weeks (as of this writing) and therefore the number of experiments that have been performed on it is limited.…”

Section: Recognition Resultsmentioning

confidence: 99%

“…Previous work focused on a 1K word task, Resource Management (RM) [18], which could be handled adequately with the TS decoder. (The same decoder was also used on the ATIS task [13].)…”

Section: Introductionmentioning

confidence: 99%

The Lincoln large-vocabulary HMM CSR

Paul

1992

Proceedings of the Workshop on Speech and Natural Language - HLT '91

View full text Add to dashboard Cite

The work described here focuses on recognition of the Wall Street Journal (WSJ) pilot database [17], a new CSR database which supports 5K, 20K, and up to 64K-word CSR tasks. The original Lincoln Tied-Mixture HMM CSR was implemented using a time-synchronous beam-pruned search of a static network [14] and does not extend well to this task because the recognition network would be too large for currently practical workstations. Therefore, the recognizer has been converted to a stack decoder-based search strategy [I,7,16]. This decoder has been shown to function effectively on up to 64K-word recognition of continuous speech. This paper describes the acoustic modeling techniques and the implementation of the stack decoder used to obtain these results.

show abstract

“…It has enabled us to use cross-word-bonndary triphone models and trigram language models with ease. During most of the development of the system we used the 1000-Word RM cospus [8] for testing. More recently, the system has been used for recognizing spontaneous speech from the ATIS corpus, which contains many spontaneous speech effects, such as partial words, nonspeech sounds, extraneous.noises, false starts, etc.…”

Section: Byblosmentioning

confidence: 99%

Comparative experiments on large vocabulary speech recognition

Kubala

Anastasakos²,

Makhoul³

et al.

Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

This paper describes several key experiments in large vocabulay speech recognition. We demonstrate that, counter to our intuitions, given a fixed amount of training speech, the number of training speakers has little effect on the accuracy. We show how much speech is needed for speaker-independent (SI) recognition in order to achieve the same performance as speakerdependent (SD) recognition. We demonstrate that, though the N-Best Paradigm works quite well up to vocabularies of 5,000 words, it begins to break down with 20,000 words and long sentences. We compare the performance of two feature preprocessing algorithms for microphone independence and we describe a new microphone adaptation algorithm based on selection among several codebook transformations.

show abstract

The DARPA 1000-word resource management database for continuous speech recognition

Abstract: P a t t i Price W i l l i a m M. Fisher J a r e d B e r n s t e i n

Cited by 239 publications

References 3 publications

A Comparison of Perceptually Motivated Loss Functions for Binary Mask Estimation in Speech Separation

A Comparison of Perceptually Motivated Loss Functions for Binary Mask Estimation in Speech Separation

The Lincoln large-vocabulary HMM CSR

Comparative experiments on large vocabulary speech recognition

Contact Info

Product

Resources

About