We first elaborate on methodologies for realistic data contamination, with a particular emphasis on DNN training with simulated data. This thesis addresses the latter scenario and proposes some novel techniques, architectures, and algorithms to improve the robustness of distant-talking acoustic models. 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. 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 re- verberant environments. Among the other achievements, building computers that understand speech represents a crucial leap towards intelligent machines.
The same trend in performance is confirmed either using a high-quality training set of small size, and a large one.ĭeep learning is an emerging technology that is considered one of the most promising directions for reaching higher levels of artificial intelligence. The experimental results, obtained using both real and simulated data, show a significant advantage in using these three methods, overall providing a 15% error rate reduction compared to the baseline systems. In this paper, we revise this classical approach in the context of modern DNN-HMM systems, and propose the adoption of three methods, namely, asymmetric context windowing, close-talk based supervision, and close-talk based pre-training. One of the most effective approaches to derive a robust acoustic modeling is based on using contaminated speech, which proved helpful in reducing the acoustic mismatch between training and testing conditions. To this end, several advances in speech enhancement, acoustic scene analysis as well as acoustic modeling, have recently contributed to improve the state-of-the-art in the field. Robustness of distant speech recognition in adverse acoustic conditions, on the other hand, remains a crucial open issue for future applications of human-machine interaction. Despite the significant progress made in the last years, state-of-the-art speech recognition technologies provide a satisfactory performance only in the close-talking condition.
0 kommentar(er)
