Unsupervised training of acoustic models for large vocabulary continuous speech recognition

By Frank Wessel, Hermann Ney. 2005

181 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing, 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 Natural Language Processing

In Speech & Audio

In Signal Processing

Citations in the corpus

Iterative Pseudo-Labeling for Speech Recognition (2020, neutral): “Semi-supervision in ASR is well-studied [15, 16, 17, 18, 19, 20]; our work builds primarily on recent work with end-to-end systems, especially PL [9, 1].”
Self-Training for End-to-End Speech Recognition (2019, background): “confidence-based filtering [4,5] and agreement-based selection [20], which also takes advantage of multiple systems.”
Contrastive Semi-Supervised Learning for ASR (2021, methodology): “Using multiple rounds of pseudo-labeling for model pre-training was found very effective for the classical GMM/HMM systems in the mid 2000s [5] and more recently for neural systems [11, 32, 8].”
slimIPL: Language-Model-Free Iterative Pseudo-Labeling (2020, methodology): “ and web-scale bitext mining [44]; • automatic speech recognition (ASR): representation learning [45, 2, 46, 47], local prior matching [4], adversarial training [48], back-translation [49] and others [50, 51, 52, 53, 54]. Below, we give an overview of the approaches in ASR that are most recent and r”
Semi-supervised GMM and DNN acoustic model training with multi-system combination and confidence re-calibration (2013, background): “For this reason, much effort has been devoted to the unsupervised and semi-supervised acoustic model training [1, 2, 3, 4, 5, 6, 7, 8] to exploit the untranscribed data.”
Machine Learning Paradigms for Speech Recognition: An Overview (2013, methodology): “Representative work includes [162]–[164], where an ASR trained on a small transcribed set is used to generate transcriptions for larger quantities of un-transcribed data first.”
Large scale weakly and semi-supervised learning for low-resource video ASR (2020, methodology): “Reducing the amount of manual transcription for building speech recognition systems has been a constant research theme over the past three decades [40, 20, 9, 5, 41, 42] given the revolutionary increase and access to unlabeled data and computational resources.”
Semi-Supervised DNN Training with Word Selection for ASR (2017, methodology): “The word-selection can be found in GMM experiments from Wessel [3].”
Mitigating Noisy Inputs for Question Answering (2019, methodology): “Using unsupervised approaches for ASR [20, 21] and training ASR models for decoding Quizbowl or Jeopardy! words are avenues for further exploration.”
Unsupervised training and directed manual transcription for LVCSR (2010, methodology): “Most previous studies of unsupervised training examined Maximum Likelihood (ML) estimation techniques (Kemp and Waibel, 1999; Lamel et al., 2001; Lamel et al., 2002; Wessel and Ney, 2005; Riccardi and Hakkani-Tur, 2003; Kamm and Meyer, 2002).”
Speech Recognition by Machine, A Review (2010, methodology): “hese have been achieved using some parameters choosen in two ways, namely i) to maximize the likelihood of observed speech signals, or ii) to minimize the number of classification errors. Dat Tat Tran[75] have proposed various models namely, i) the FE-HMM,NC-FE-HMM,FE-GMM,NC-FEGMM,FE-VQ and NC-FE-VQ”