This list is ever-growing… if you have a paper to add, let me know:)



i-vectors

Dehak et al. (2010) Front-End Factor Analysis For Speaker Verification

Seminal i-vector paper. The application is speaker identification.

Soan et al. (2013) Speaker Adaptation of Neural Network Acoustic Models Using I-Vectors

First use of i-vectors for DNN speaker adaptation in ASR.


Soan (2013) i-vector extraction and appendage



Context-Dependent Triphone State-Tying

Young et al. (1994) Tree-based state tying for high accuracy acoustic modelling



Weighted Finite-State Transducer Decoding

Mohri et al. (2001) Weighted Finite-State Transducers in Speech Recognition



MLLR Adaptation

Leggetter & Woodland (1995) Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models



Hybrid DNN-HMM Approach

Dahl et al. (2012) Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition