Deep neural network features and semi-supervised training for low resource speech recognition

By Samuel Thomas, M. Seltzer, Kenneth Ward Church, Hynek Hermansky. 2013

154 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Representation & Self-Supervised Learning, 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 Representation & Self-Supervised Learning

In Speech & Audio

In Signal Processing

Citations in the corpus

Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition (2020, methodology): “Self-training has been a popular technique in ASR studied extensively in the literature [25–33].”
Improved Noisy Student Training for Automatic Speech Recognition (2020, background): “Self-training has a long history of being applied to ASR through numerous studies, e.g., [12, 13, 14, 15, 16, 17, 18, 19].”
Unsupervised Speech Representation Learning Using WaveNet Autoencoders (2019, background): “In such scenario, limited amounts of data may be sufficient to learn an acoustic model on the representation discovered without supervision, but insufficient to learn the acoustic model and a data representation in a fully supervised manner [15], [16].”
Lessons from Building Acoustic Models with a Million Hours of Speech (2019, methodology): “Several methods to estimate word and frame level token conﬁdence from speech lattices or hypotheses have been developed ([21], [22]).”
Deep Contextualized Acoustic Representations for Semi-Supervised Speech Recognition (2019, methodology): “The most commonly-used SSL approach in ASR is self-training [1, 2, 3, 4, 5].”
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].”
Semi-supervised ASR by End-to-end Self-training (2020, background): “It has been shown to be very effective with traditional ASR pipelines [1, 2, 3, 4].”
Investigation of transfer learning for ASR using LF-MMI trained neural networks (2017, methodology): “Supervised training using out-of-domain data is also a form of pretraining and it has been used to learn multilingual bottleneck features in [10, 11].”
Semi-Supervised DNN Training with Word Selection for ASR (2017, methodology): “The per-sentence confidence csent is typically calculated as the average of the word confidences [4, 5, 6, 9]: csent = 1”
Elastic spectral distortion for low resource speech recognition with deep neural networks (2013, background): “Those works focused on how to transfer the acoustics of other resource-rich languages to the target language [7, 8] or to make the language-independent feature front-end [9].”
Almost-unsupervised Speech Recognition with Close-to-zero Resource Based on Phonetic Structures Learned from Very Small Unpaired Speech and Text Data (2018, background): “Although substantial efforts have been reported on semi-supervised ASR [1, 2, 3, 4, 5, 6], in most cases a large amount of speech data including a good portion annotated were still needed.”