Cumulative Adaptation For BLSTM Acoustic Models

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykitza2019cumulative

Related papers

• A Comparison Of Adaptation Techniques And Recurrent Neural Network Architectures (2018)3.58
• Speaker Adaptation For End-to-end Speech Recognition Systems In Noisy Environments (2022)0.00
• End-to-end Adaptation With Backpropagation Through WFST For On-device Speech Recognition System (2019)5.24
• Bayesian Learning For Deep Neural Network Adaptation (2020)9.76
• Multi-staged Cross-lingual Acoustic Model Adaption For Robust Speech Recognition In Real-world Applications -- A Case Study On German Oral History Interviews (2020)0.00
• Layer-wise Fast Adaptation For End-to-end Multi-accent Speech Recognition (2022)9.76
• Factorised Speaker-environment Adaptive Training Of Conformer Speech Recognition Systems (2023)0.00
• A Unified Speaker Adaptation Method For Speech Synthesis Using Transcribed And Untranscribed Speech With Backpropagation (2019)0.00