Semi-Supervised Training of Acoustic Models Using Lattice-Free MMI
By Vimal Manohar, Hossein Hadian, Daniel Povey, Sanjeev Khudanpur. 2018
83 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Optimization & Training, Speech & Audio
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
- Michael Auli
- Alexei Baevski
- Wei-Ning Hsu
- Gabriel Synnaeve
- Abdel-rahman Mohamed
- Jianfeng Gao
- Mohit Bansal
- Luke S. Zettlemoyer
In Optimization & Training
- Yatharth Saraf
- Julian Salazar
- Awni Y. Hannun
- Ann Lee
- Vitaliy Liptchinsky
- Geoffry Zweig
- Alex Xiao
- Sergey Edunov
In Speech & Audio
- Wei-Ning Hsu
- Abdel-rahman Mohamed
- Alexei Baevski
- Michael Auli
- Gabriel Synnaeve
- Alexis Conneau
- Ann Lee
- Ronan Collobert
Citations in the corpus
- Unsupervised Speech Recognition (2021, methodology): “, 2020a), or with separate objectives and weights (Veselỳ et al., 2017; Manohar et al., 2018; Hsu et al., 2020).”
- 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].”
- Semi-Supervised Speech Recognition via Local Prior Matching (2020, background): “, 2017; Parthasarathi & Strom, 2019) and weak distillation (also known as selftraining or pseudo-labeling) (Veselỳ et al., 2017; Manohar et al., 2018; Li et al., 2019; Kahn et al., 2019a) have also achieved great success in semi-supervised learning for ASR.”
- Large scale weakly and semi-supervised learning for low-resource video ASR (2020, methodology): “Incorporating the LM information within a sequence discriminative loss function for self-labeling was proven to be a difficult task given the noise in labels [46, 48, 38].”