Anton Mitrofanov

room impulse response (3) neural network language model (2) automatic speech recognition (2) acoustic model (2) speaker diarization (2) speaker adaptation (2) acoustic feature extraction (1) word error rate (1) lattice rescoring (1) distant speech recognition (1) overlapping speech (1) diarization error rate (1) non-autoregressive language model (1) channel verification (1) multi-speaker detection (1) target-speaker voice activity detection (1) transformer architecture (1) r-vector embedding (1) binary classification (1) embedding learning (1)