α-Jacobian environmental adaptation

Cerisara, Christophe; Rigazio, Luca; Junqua, Jean‐Claude

doi:10.1016/j.specom.2003.08.003

Cited by 13 publications

(14 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Adaptation to noisy speech is different from speaker adaptation in that noisy speech has not only convolutive factors, but also additive factors in the spectral domain. The vector Taylor series based approach [59], Jacobian adaptation [73], and their extensions (e.g., [4], [51]) have been extensively studied.…”

Section: Adaptation To Noisy Speechmentioning

confidence: 99%

Acoustic Model Adaptation for Speech Recognition

Sairyo

2010

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYStatistical speech recognition using continuous-density hidden Markov models (CDHMMs) has yielded many practical applications. However, in general, mismatches between the training data and input data significantly degrade recognition accuracy. Various acoustic model adaptation techniques using a few input utterances have been employed to overcome this problem. In this article, we survey these adaptation techniques, including maximum a posteriori (MAP) estimation, maximum likelihood linear regression (MLLR), and eigenvoice. We also present a schematic view called the adaptation pyramid to illustrate how these methods relate to each other. key words: speech recognition, acoustic model adaptation, hidden Markov models

show abstract

Section: Adaptation To Noisy Speechmentioning

confidence: 99%

Acoustic Model Adaptation for Speech Recognition

Sairyo

2010

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…C,+n =HdiagK aN H1 acn S+aN) (2) where N is the filter-bank energies (FBE) vector of the training noise reference, S is the FBE vector of the noisy speech model, H is the FF matrix transformation and H-1 is its inverse [10]. The quotient is computed element by element and diago is the diagonal matrix formed with elements of the vector inside.…”

Section: Model-dependent Noise Reference Jacobian Adaptationmentioning

confidence: 99%

“…Jacobian Adaptation (JA) is a model adaptation technique used to adapt a set of models from certain noise conditions to other conditions in order to alleviate the mismatch between training and testing. In previous works [1][2][3][4][5] it has been shown that JA improves the results of both speech and speaker recognition systems in noisy conditions. This technique adapts the models on the basis of the difference between the training and the testing noise conditions.…”

Section: Introductionmentioning

confidence: 99%

“…In [1] the noise conditions are supposed to be known, which is not generally true in a real situation. In [2] the noise estimation is obtained by averaging the N frames of the signal with the lowest energy but this procedure biases the estimation toward lower values. In [3][4] the noise is estimated by averaging a constant number of frames at the beginning of the signals.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Jacobian Adaptation with Continuous Noise Estimation for Real Speaker Verification Applications

Anguita

Hernando

2006

2006 IEEE Odyssey - The Speaker and Language Recognition Workshop

View full text Add to dashboard Cite

Jacobian Adaptation (JA) of the acoustic models is a fast adaptation technique that has been successfully used in both speech and speaker recognition. This technique adapts the acoustic models on the basis of the difference between the testing and the training noise conditions. For this reason, a noise reference of both the training and the testing phase is needed. In previous works, the noise conditions have been commonly supposed to be known or estimated from the first part of the signal. In this work we propose to obtain the noise references by using continuous noise estimation methods, which are more appropriate for real applications and can deal with non-stationary noises. Several noise estimation methods are compared: Recursive Averaging (RA), Minimum Statistics (MS) and Minima Controlled Recursive Averaging (MCRA). The obtained results show that these techniques are effective for JA.

show abstract

“…Other techniques focus on noise compensation, for example, parallel model combination (PMC) [23]- [25], or Jacobian environmental adaptation [26], [27], assuming the availability of a statistical model of the noise or environment. Researchers in [28] and [29] have discussed the use of microphone arrays to improve noise robustness.…”

mentioning

confidence: 99%

Robust Speaker Recognition in Noisy Conditions

Hazen

Glass³

et al. 2007

IEEE Trans. Audio Speech Lang. Process.

213

115

View full text Add to dashboard Cite

Abstract-This paper investigates the problem of speaker identification and verification in noisy conditions, assuming that speech signals are corrupted by environmental noise, but knowledge about the noise characteristics is not available. This research is motivated in part by the potential application of speaker recognition technologies on handheld devices or the Internet. While the technologies promise an additional biometric layer of security to protect the user, the practical implementation of such systems faces many challenges. One of these is environmental noise. Due to the mobile nature of such systems, the noise sources can be highly time-varying and potentially unknown. This raises the requirement for noise robustness in the absence of information about the noise. This paper describes a method that combines multicondition model training and missing-feature theory to model noise with unknown temporal-spectral characteristics. Multicondition training is conducted using simulated noisy data with limited noise variation, providing a "coarse" compensation for the noise, and missing-feature theory is applied to refine the compensation by ignoring noise variation outside the given training conditions, thereby reducing the training and testing mismatch. This paper is focused on several issues relating to the implementation of the new model for real-world applications. These include the generation of multicondition training data to model noisy speech, the combination of different training data to optimize the recognition performance, and the reduction of the model's complexity. The new algorithm was tested using two databases with simulated and realistic noisy speech data. The first database is a redevelopment of the TIMIT database by rerecording the data in the presence of various noise types, used to test the model for speaker identification with a focus on the varieties of noise. The second database is a handheld-device database collected in realistic noisy conditions, used to further validate the model for real-world speaker verification. The new model is compared to baseline systems and is found to achieve lower error rates.

show abstract

α-Jacobian environmental adaptation

Cited by 13 publications

References 34 publications

Acoustic Model Adaptation for Speech Recognition

Acoustic Model Adaptation for Speech Recognition

Jacobian Adaptation with Continuous Noise Estimation for Real Speaker Verification Applications

Robust Speaker Recognition in Noisy Conditions

Contact Info

Product

Resources

About