Reverberation Model-Based Decoding in the Logmelspec Domain for Robust Distant-Talking Speech Recognition

• Published in: IEEE transactions on audio, speech, and language processing Vol. 18; no. 7; pp. 1676 - 1691
• Main Authors: Sehr, Armin, Maas, Roland, Kellermann, Walter
• Format: Journal Article
• Language: English
• Published: IEEE 01.09.2010
• Subjects: Acoustic modeling; Algorithms; Automatic speech recognition; Constraint optimization; Contracts; Decoding; distant-talking automatic speech recognition (ASR); Estimates; Hidden Markov models; Loudspeakers; Mathematical models; Microphones; model-based dereverberation; Nonlinearity; Optimization; Recognition; Reverberation; reverberation model; robust ASR; Robustness; Speech recognition; Training

The REMOS (REverberation MOdeling for Speech recognition) concept for reverberation-robust distant-talking speech recognition, introduced in "Distant-talking continuous speech recognition based on a novel reverberation model in the feature domain" (A. Sehr , in Proc. Interspeech, 2006, pp....