A comparison of front-ends for bitstream-based ASR over IP

Abstract

Automatic Speech Recognition (ASR) is called to play a relevant role in the provision of spoken interfaces for IP-based applications. However, as a consequence of the transit of the speech signal over these particular networks, ASR systems need to face two new challenges: the impoverishment of the speech quality due to the compression needed to fit the channel capacity and the inevitable occurrence of packet losses.In this framework, bitstream-based approaches that obtain the ASR feature vectors directly from the coded bitstream, avoiding the speech decoding process, have been proposed ([4,7,10,15], among others) to improve the robustness of ASR systems. LSP (Line Spectral Pairs) are the preferred set of parameters for the description of the speech spectral envelope in most of the modern speech coders. Nevertheless, LSP have proved to be unsuitable for ASR, and they must be transformed into cepstrum-type parameters. In this paper we comparatively evaluate the robustness of the most significant LSP to cepstrum transformations in a simulated VoIP (Voice over IP) environment which includes two of the most popular codecs used in that network (G.723.1 and G.729) and several network conditions. In particular, we compare 'pseudocepstrum' [9], an approximated but straightforward transformation of LSP into LP cepstral coefficients, with a more computationally demanding but exact one. Our results show that pseudocepstrum is preferable when network conditions are good or computational resources low, while the exact procedure is recommended when network conditions become more adverse.

Robust Distributed Speech Recognition Using Auditory Modelling

“…In [27][28][29], a voice over IP (VoIP) channel is simulated using such a model. References [30,31] simulate IP channels and use a 2-state Gilbert model to simulate burst type packet loss on the channel.…”