Deep Learning for Distant Speech Recognition

Ravanelli, Mirco (2017) Deep Learning for Distant Speech Recognition. PhD thesis, University of Trento.

[img]PDF - Doctoral Thesis
Restricted to Repository staff only until 9999.
Available under License Creative Commons Attribution.

[img]PDF - Disclaimer
Restricted to Repository staff only until 9999.



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.

Item Type:Doctoral Thesis (PhD)
Doctoral School:Information and Communication Technology
PhD Cycle:29
Subjects:Area 09 - Ingegneria industriale e dell'informazione > ING-INF/05 SISTEMI DI ELABORAZIONE DELLE INFORMAZIONI
Uncontrolled Keywords:Deep Learning, Distant Speech Recognition, Deep Neural Networks.
Funders:Fondazione Bruno Kessler
Repository Staff approval on:18 Dec 2017 12:26

Repository Staff Only: item control page