Cumulative Adaptation for BLSTM Acoustic Models
This work addresses robust speech recognition for automatic speech recognition systems, but it is incremental as it builds on existing adaptation techniques.
The paper tackles robust speech recognition by applying cumulative adaptation methods to a BLSTM acoustic model, achieving an 8% relative improvement in word error rate with i-vector adaptation and an additional 5% with a second-pass adaptation.
This paper addresses the robust speech recognition problem as an adaptation task. Specifically, we investigate the cumulative application of adaptation methods. A bidirectional Long Short-Term Memory (BLSTM) based neural network, capable of learning temporal relationships and translation invariant representations, is used for robust acoustic modelling. Further, i-vectors were used as an input to the neural network to perform instantaneous speaker and environment adaptation, providing 8\% relative improvement in word error rate on the NIST Hub5 2000 evaluation test set. By enhancing the first-pass i-vector based adaptation with a second-pass adaptation using speaker and environment dependent transformations within the network, a further relative improvement of 5\% in word error rate was achieved. We have reevaluated the features used to estimate i-vectors and their normalization to achieve the best performance in a modern large scale automatic speech recognition system.