Exploiting deep neural networks for detection-based speech recognition

Siniscalchi, Sabato Marco; Yu, Dong; Deng, Li; Lee, Chin‐Hui

doi:10.1016/j.neucom.2012.11.008

Cited by 103 publications

(36 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such an optimisation approach can be used for deep neural networks [41], [42]. The optimised 2LP is a potential base unit for deep learning, like for boosting [11], [16], [20], [43], [44].…”

Section: Discussionmentioning

confidence: 99%

Optimal Training Parameters and Hidden Layer Neuron Number of Two-Layer Perceptron for Generalised Scaled Object Classification Problem

Romanuke

2015

Information Technology and Management Science

View full text Add to dashboard Cite

-The research is focused on optimising two-layer perceptron for generalised scaled object classification problem. The optimisation criterion is minimisation of inaccuracy. The inaccuracy depends on training parameters and hidden layer neuron number. After its statistics is accumulated, minimisation is executed by a numerical search. Perceptron is optimised additionally by extra training. As it is done, the classification error percentage does not exceed 3 % in case of the worst scale distortion.

show abstract

Section: Discussionmentioning

confidence: 99%

Optimal Training Parameters and Hidden Layer Neuron Number of Two-Layer Perceptron for Generalised Scaled Object Classification Problem

Romanuke

2015

Information Technology and Management Science

View full text Add to dashboard Cite

show abstract

“…There has also been a great deal of work in speech recognition on acoustic observation models based on sub-phonetic features and on feature classification (Kirchhoff et al, 2002;Metze and Waibel, 2002;Eide, 2001;Frankel and King, 2001;Wester et al, 2004b;King et al, 2007;Cetin et al, 2007;Morris and Fosler-Lussier, 2008;Siniscalchi et al, 2013). Such methods can be combined with articulatory feature-based pronunciation models to build complete speech recognizers.…”

Section: Related Workmentioning

confidence: 99%

Articulatory feature-based pronunciation modeling

Livescu

Jyothi

Fosler‐Lussier

2016

Computer Speech & Language

View full text Add to dashboard Cite

Please cite this article in press as: Livescu, K., et al., Articulatory feature-based pronunciation modeling. Comput. Speech Lang. (2015), http://dx. AbstractSpoken language, especially conversational speech, is characterized by great variability in word pronunciation, including many variants that differ grossly from dictionary prototypes. This is one factor in the poor performance of automatic speech recognizers on conversational speech, and it has been very difficult to mitigate in traditional phone-based approaches to speech recognition. An alternative approach, which has been studied by ourselves and others, is one based on sub-phonetic features rather than phones. In such an approach, a word's pronunciation is represented as multiple streams of phonological features rather than a single stream of phones. Features may correspond to the positions of the speech articulators, such as the lips and tongue, or may be more abstract categories such as manner and place.This article reviews our work on a particular type of articulatory feature-based pronunciation model. The model allows for asynchrony between features, as well as per-feature substitutions, making it more natural to account for many pronunciation changes that are difficult to handle with phone-based models. Such models can be efficiently represented as dynamic Bayesian networks. The feature-based models improve significantly over phone-based counterparts in terms of frame perplexity and lexical access accuracy. The remainder of the article discusses related work and future directions.

show abstract

“…However in this paper, we propose to incorporate phonological information to improve the parameter initialization of the unseen phonemes when extending the CTC output layer. Inspired by the Automatic Speech Attribute Transcription (ASAT) framework [14], we first train a phonological attribute detector that detects a collection of phonological attribute cues, and then integrate such cues to make predictions of the same IPA-based multilingual phoneme targets. When a new language arrives, the corresponding phonological attributes of unseen phonemes can be derived from phonological rules.…”

Section: Introductionmentioning

confidence: 99%

Fast Language Adaptation Using Phonological Information

Tong¹,

Garner²,

Bourlard³

2018

Interspeech 2018

View full text Add to dashboard Cite

Phoneme-based multilingual connectionist temporal classification (CTC) model is easily extensible to a new language by concatenating parameters of the new phonemes to the output layer. In the present paper, we improve cross-lingual adaptation in the context of phoneme-based CTC models by using phonological information. A universal (IPA) phoneme classifier is first trained on phonological features generated from a phonological attribute detector. When adapting the multilingual CTC to a new, never seen, language, phonological attributes of the unseen phonemes are derived based on phonology and fed into the phoneme classifier. Posteriors given by the classifier are used to initialize the parameters of the unseen phonemes when extending the multilingual CTC output layer to the target language. Adaptation experiments show that the proposed initialization approaches further improve the cross-lingual adaptation on CTC models and yield significant improvements over Deep Neural Network / Hidden Markov Model (DNN/HMM)-based adaptation using limited data.

show abstract

Exploiting deep neural networks for detection-based speech recognition

Cited by 103 publications

References 63 publications

Optimal Training Parameters and Hidden Layer Neuron Number of Two-Layer Perceptron for Generalised Scaled Object Classification Problem

Optimal Training Parameters and Hidden Layer Neuron Number of Two-Layer Perceptron for Generalised Scaled Object Classification Problem

Articulatory feature-based pronunciation modeling

Fast Language Adaptation Using Phonological Information

Contact Info

Product

Resources

About