Performance of distant-talking speech recognizers in real noisy environments can be increased using a microphone array. In this work we propose an N-best extension of the Limabeam algorithm, which is a likelihood-based adaptive filter-and-sum beamformer. We show that this algorithm can be used to optimize the noisy acoustic features using in parallel the N-best hypothesized transcriptions generated at a first recognition step. The parallel and independent optimizations increase the likelihood of minimal word error rate hypotheses and the resulting N-best hypotheses list is automatically re-ranked. Results show improvements over delay-and-sum beamforming and Unsuper- vised Limabeam on a real database with considerable amount of noise and limited reverberation.
Improving robustness of a likelihood-based beamformer in a real environment for automatic speech recognition
Omologo, Maurizio
2006
Abstract
Performance of distant-talking speech recognizers in real noisy environments can be increased using a microphone array. In this work we propose an N-best extension of the Limabeam algorithm, which is a likelihood-based adaptive filter-and-sum beamformer. We show that this algorithm can be used to optimize the noisy acoustic features using in parallel the N-best hypothesized transcriptions generated at a first recognition step. The parallel and independent optimizations increase the likelihood of minimal word error rate hypotheses and the resulting N-best hypotheses list is automatically re-ranked. Results show improvements over delay-and-sum beamforming and Unsuper- vised Limabeam on a real database with considerable amount of noise and limited reverberation.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
