Noise adaptation algorithms for robust speech recognition

Cung, Hong Minh; Normandin, Yves

doi:10.1016/0167-6393(93)90098-6

Cited by 11 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…O c ( ? w a ) (6) are the delta and delta-delta parameters respectively. If statistics about the correlation between successive frames are known, for example EfS c ( +w)S c ( ?w) T g, then statistics, including correlations, exist for the above expressions and the corrupted delta and deltadelta parameters may be estimated using the standard static parameter mismatch function.…”

Section: Mismatch Function For Dynamic Parameters In Additive Noisementioning

confidence: 99%

See 1 more Smart Citation

Robust continuous speech recognition using parallel model combination

Gales

Young

1996

IEEE Trans. Speech Audio Process.

378

146

View full text Add to dashboard Cite

This paper addresses the problem of automatic speech recognition in the presence of interfering noise. It focuses on the Parallel Model Combination (PMC) scheme, which has been shown to be a powerful technique for achieving noise robustness. Most experiments reported on PMC to date have been on small, 10-50 word vocabulary systems. Experiments on the Resource Management (RM) database, a 1000 word continuous speech recognition task, reveal compensation requirements not highlighted by the smaller vocabulary tasks. In particular, that it is necessary to compensate the dynamic parameters as well as the static parameters to achieve good recognition performance. The database used for these experiments was the RM speaker independent task with either Lynx Helicopter noise or Operation Room noise from the NOISEX-92 database added. The experiments reported here used the HTK RM recogniser developed at CUED modi ed to include PMC based compensation for the static, delta and delta-delta parameters. After training on clean speech data,the performance of the recogniser was found to be severely degraded when noise was added to the speech signal at between 10dB and 18dB. However, using PMC the performance was restored to a level comparable with that obtained when training directly in the noise corrupted environment.

show abstract

Section: Mismatch Function For Dynamic Parameters In Additive Noisementioning

confidence: 99%

“…The Lynx helicopter noise was added to the clean RM data to give a SNR of approximately 18dB 6 . To achieve this SNR, the noise was attenuated by 20dB.…”

Section: Databasementioning

confidence: 99%

Robust continuous speech recognition using parallel model combination

Gales

Young

1996

IEEE Trans. Speech Audio Process.

378

146

View full text Add to dashboard Cite

show abstract

“…The technique of hierarchical spectral clustering has also been applied to the spectral normalization of noisy speech [40]. This is a non-supervised technique which builds up the adaptation codebook iteratively;…”

Section: Noise Adaptation Methodsmentioning

confidence: 99%

Problems and solutions for noisy speech recognition

Haton

1994

J. Phys. IV France

View full text Add to dashboard Cite

Automatic speech recognition has reached high level performances but it usually fails in coping with real-life, noisy environments. An essential reason is the mismatch between the conditions in which a system is trained and used. A large number of solutions have been proposed in order to solve this problem. Those solutions can be classified into two main, non exclusive categories. Firstly, signal processing and parametrization techniques can be used as a preprocessing step in order to enhance the SNR of the corrupted speech signal. Secondly, the different steps of the pattern matching process can be modified in order to account for the effects of noise. This paper presents a brief survey of the noisy speech recognition field. We first summarize the major difficulties that are encountered in the development of a system, and we then introduce three main categories of solutions dealing with acoustical preprocessing and parametrization of the speech signal, statistical modelling, and recognition techniques

show abstract

“…• In [29], speaker adaptation methods were compared, and fuzzy HMM produced worse results (1990), while in [34], fuzzy HMM were deemed at least as good in what concerns robustness of speech recognition algorithms (1990); • In [11], robust speech recognition using fuzzy clustering, produced much better results than hard clustering (but no other methods were compared); • In [46], Fuzzy GMM is found to be more efective than GMM for speaker recognitions; • In [21], fuzzy sets yeld better results than MFCC when combining auditory representations (1994); • In [45], fuzzy techniques for speech segmentation, produced results equal to NN but slightly worse than manual segmentation (2001).…”

Section: Snlp Conferencesmentioning

confidence: 99%

A critical survey on the use of Fuzzy Sets in Speech and Natural Language Processing

Carvalho

Batista

Coheur

2012

2012 IEEE International Conference on Fuzzy Systems

View full text Add to dashboard Cite

This paper shows how the use and applications of Fuzzy Sets (FS) in Speech and Natural Language Processing (SNLP) have seen a steady decline to a point where FS are virtually unknown or unappealing for most of the researchers currently working in the SNLP field, tries to find the reasons behind this decline, and proposes some guidelines on what could be done to reverse it and make FS assume a relevant role in SNLP.

show abstract

Noise adaptation algorithms for robust speech recognition

Cited by 11 publications

References 7 publications

Robust continuous speech recognition using parallel model combination

Robust continuous speech recognition using parallel model combination

Problems and solutions for noisy speech recognition

A critical survey on the use of Fuzzy Sets in Speech and Natural Language Processing

Contact Info

Product

Resources

About