ROBUST SPEECH RECOGNITION USING DYNAMIC NOISE ADAPTATION

Robust ASR

Presented by: Steven Rennie, Author(s): Steven Rennie, Pierre Dognin, Petr Fousek, IBM, United States

Dynamic noise adaptation (DNA) [1, 2] is a model-based technique for improving automatic speech recognition (ASR) performance in noise. DNA has shown promise on artificially mixed data such as the Aurora II and DNA+Aurora II tasks [1]—significantly outperforming well-known techniques like the ETSI AFE and fMLLR [2]—but has never been tried on real data. In this paper, we present new results generated by commercial-grade ASR systems trained on large amounts of data. We show that DNA improves upon the performance of the spectral subtraction (SS) and stochastic fMLLR algorithms of our embedded recognizers, particularly in unseen noise conditions, and describe how DNA has been evolved to become suitable for deployment in low-latency ASR systems. DNA improves our best embedded system, which utilizes SS, fMLLR, and fMPE [4] by over 22% relative at SNRs below 6 dB, reducing the word error rate in these adverse conditions from 4.24% to 3.29%.

You need the Flash Player.

Share:

Download subtitles | Enlarge video

1. slide