Multilingual acoustic modeling for speech recognition based on subspace Gaussian Mixture Models

By Lukáš Burget, Petr Schwarz, Mohit Agarwal, Pinar Akyazi, Kai Feng, Arnab Ghoshal, Ondrej Glembek, Nagendra Kumar Goel, Martin Karafiát, Daniel Povey and 3 more. 2010

196 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Speech & Audio, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Speech & Audio

In Signal Processing

Citations in the corpus

SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network (2021, neutral): “Multi-lingual training [10, 11], multi-domain training [12, 13], unsupervised pre-training [14, 15], semi-supervised learning [16, 17] and transfer learning [18, 19] are some techniques proposed in the literature to enhance generalization.”
Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters (2020, methodology): “Introduction The use of multilingual ASR systems [1, 2, 3, 4, 5, 6, 7, 8, 9] that simultaneously transcribe multiple languages has recently become popular to increase language coverage, but covering all of the world’s ∼7000 languages is still far ahead.”
Multilingual Speech Recognition with a Single End-to-End Model (2017, background): “…continuous speech recognizers are severly limited [1] These challenges have meant that there has been a perennial interest in multilingual and cross-lingual models which allow for knowledge transfer across languages, and thus relieve burdensome data requirements [2, 3, 4, 5, 6, 7, 8, 9, 10, 11].”
Unsupervised Pretraining Transfers Well Across Languages (2020, background): “Burget et al. [10] shares the parameters of a Gaussian Mixture Model.”
Unsupervised Cross-lingual Representation Learning for Speech Recognition (2020, background): “This has been a long standing interest in the speech community [1, 2, 3, 4, 5, 6, 7] which includes systems able to transcribe multiple languages [8, 9, 10, 11, 12].”
Multilingual training of deep neural networks (2013, methodology): “The subspace Gaussian mixture model (SGMM) [8] has been shown to be suitable for cross-lingual modeling without requiring an explicit mapping between phone units in different languages [9, 10].”
Cross-language knowledge transfer using multilingual deep neural network with shared hidden layers (2013, background): “subspace GMMs [19] might be the closest to DNN.”
Scaling Speech Technology to 1, 000+ Languages (2023, methodology): “This has several important applications: despite much work on multilingual speech recognition [Burget et al., 2010, Lin et al., 2009, Heigold et al., 2013, Bourlard et al., 2011, Cho et al., 2018, Toshniwal et al., 2018, Kannan et al., 2019, Li et al., 2019, Pratap et al., 2020b], many deployed…”
Multilingual acoustic models using distributed deep neural networks (2013, methodology): “In this approach, multiple tasks are learned in parallel and use a shared representation [7, 25].”
Multilingual MLP features for low-resource LVCSR systems (2012, methodology): “More recently cross-lingual training with Subspace Gaussian Mixture Models (SGMM) [4] have also been proposed for this task.”
Multitask Learning of Deep Neural Networks for Low-Resource Speech Recognition (2015, background): “Successful examples include tied-mixture HMM [12], [13], subspace Gaussian mixture model (SGMM) [14], Bayesian sensing HMM [15], and canonical state model [16].”
Deep neural network features and semi-supervised training for low resource speech recognition (2013, background): “Multilingual training with Subspace Gaussian Mixture Models [3] have also been proposed to train acoustic models [4, 5].”
Multilingual Speech Recognition with Corpus Relatedness Sampling (2019, methodology): “For example, parameters can be shared by using posterior features from other languages [6], applying the same GMM components across different HMM states [7], training shared hidden layers in DNNs [3, 4] or LSTM [5], using language independent bottleneck features [8, 9].”
Multilingual representations for low resource speech recognition and keyword search (2015, background): “Multilingual (ML) models have been shown to outperform unilingual models for ASR in low resource languages [1–8].”
Impact of deep MLP architecture on different acoustic modeling techniques for under-resourced speech recognition (2013, methodology): “In this paper, we investigate the performance of posterior based approaches in the context of under-resourced speech recognition when a standard three-layer MLP is replaced by a deeper fivelayer MLP.”