Deep Learning for Distant Speech Recognition
It addresses the problem of robust human-machine speech interaction for users in adverse acoustic settings, representing an incremental advancement in the field.
This thesis tackled the challenge of Distant Speech Recognition (DSR) in noisy and reverberant environments by proposing novel techniques, architectures, and algorithms, resulting in improved robustness of acoustic models through extensive experimental validations on various datasets and conditions.
Deep learning is an emerging technology that is considered one of the most promising directions for reaching higher levels of artificial intelligence. Among the other achievements, building computers that understand speech represents a crucial leap towards intelligent machines. Despite the great efforts of the past decades, however, a natural and robust human-machine speech interaction still appears to be out of reach, especially when users interact with a distant microphone in noisy and reverberant environments. The latter disturbances severely hamper the intelligibility of a speech signal, making Distant Speech Recognition (DSR) one of the major open challenges in the field. This thesis addresses the latter scenario and proposes some novel techniques, architectures, and algorithms to improve the robustness of distant-talking acoustic models. We first elaborate on methodologies for realistic data contamination, with a particular emphasis on DNN training with simulated data. We then investigate on approaches for better exploiting speech contexts, proposing some original methodologies for both feed-forward and recurrent neural networks. Lastly, inspired by the idea that cooperation across different DNNs could be the key for counteracting the harmful effects of noise and reverberation, we propose a novel deep learning paradigm called network of deep neural networks. The analysis of the original concepts were based on extensive experimental validations conducted on both real and simulated data, considering different corpora, microphone configurations, environments, noisy conditions, and ASR tasks.