Joint Estimation of Articulatory Features and Acoustic Models for Low-Resource Languages
نویسندگان
چکیده
Using articulatory features for speech recognition improves the performance of low-resource languages. One way to obtain articulatory features is by using an articulatory classifier (pseudoarticulatory features). The performance of the articulatory features depends on the efficacy of this classifier. But, training such a robust classifier for a low-resource language is constrained due to the limited amount of training data. We can overcome this by training the articulatory classifier using a high resource language. This classifier can then be used to generate articulatory features for the low-resource language. However, this technique fails when high and low-resource languages have mismatches in their environmental conditions. In this paper, we address both the aforementioned problems by jointly estimating the articulatory features and low-resource acoustic model. The experiments were performed on two low-resource Indian languages namely, Hindi and Tamil. English was used as the high-resource language. A relative improvement of 23% and 10% were obtained for Hindi and Tamil, respectively.
منابع مشابه
Acoustic correlated sources direction finding in the presence of unknown spatial correlation noise
In this paper, a new method is proposed for DOA estimation of correlated acoustic signals, in the presence of unknown spatial correlation noise. By generating a matrix from the signal subspace with the Hankel-SVD method, the correlated resource information is extracted from each eigen-vector. Then a joint-diagonalization structure is constructed of the signal subspace and basis it, independent...
متن کاملArticulatory Feature based Multilingual MLPs for Low-Resource Speech Recognition
Large vocabulary continuous speech recognition is particularly difficult for low-resource languages. In the scenario we focus on here is that there is a very limited amount of acoustic training data in the target language, but more plentiful data in other languages. In our approach, we investigate approaches based on Automatic Speech Attribute Transcription (ASAT) framework, and train universal...
متن کاملInvariance and Variability in Speech: Interpreting Acoustic Evidence
The acoustic signal is the medium that is probably the most used in research on human speech production and perception and for characterizing the universal structures and units in terms of which the phonological forms of language are stored. Acoustic analysis of the speech signal also provides information which helps to characterize how particular distinctive features in a given language are im...
متن کاملUnder-resourced speech recognition based on the speech manifold
Conventional acoustic modeling involves estimating many parameters to effectively model feature distributions. The sparseness of speech and text data, however, degrades the reliability of the estimation process and makes speech recognition a challenging task. In this paper, we propose to use a nonlinear feature transformation based on the speech manifold called Intrinsic Spectral Analysis (ISA)...
متن کاملStatistical mapping between articulatory movements and acoustic spectrum using a Gaussian mixture model
In this paper, we describe a statistical approach to both an articulatory-to-acoustic mapping and an acoustic-to-articulatory inversion mapping without using phonetic information. The joint probability density of an articulatory parameter and an acoustic parameter is modeled using a Gaussian mixture model (GMM) based on a parallel acoustic-articulatory speech database. We apply the GMM-based ma...
متن کامل