Graceful degradation of speech recognition performance over lossy packet networks
نویسندگان
چکیده
This paper explores packet loss recovery in client-server Automatic Speech Recognition (ASR) systems. A forward error correction (FEC) system is designed and tested over several channel loss models, at variable amounts of data acquisition delay. In experiments with simulated packet loss, the FEC system provides robust ASR performance which degrades gracefully as packet loss rates increase. Comparing this scheme to several alternatives under low and medium loss channel conditions, we found one approach (multiple transmission plus interpolation) that yielded similar performance, but the FEC system should scale better to lower bit rate conditions.
منابع مشابه
Graceful degradation of speech recognition performance over packet-erasure networks
This paper explores packet loss recovery for automatic speech recognition (ASR) in spoken dialog systems, assuming an architecture in which a lightweight client communicates with a remote ASR server. Speech is transmitted with source and channel codes optimized for the ASR application, i.e., to minimize word error rate. Unequal amounts of forward error correction, depending on the data’s effect...
متن کاملRobust speech recognition over packet networks: an overview
Conventional circuit-switched networks are increasingly being replaced by packet-based networks for voice communication applications. Additionally, there has been an increased deployment of services supporting speech based interactions. These trends demand reliable transmission of speech data not just for playback but also to ensure acceptable automatic speech recognition (ASR) performance. In ...
متن کاملInterleaving and MMSE estimation with VQ replicas for distributed speech recognition over lossy packet networks
In this work we evaluate the performance of MMSE estimation with a media-specific FEC based on VQ replicas in comparison with MAP estimation and interleaving, both operating in a DSR system over a loss-prone packet switched network. Both schemes combine a sender-driven with a receiver-based technique and, as we show, clearly outperform the standard Aurora mitigation. However, as independent tec...
متن کاملSpeech Coding and Transmission for Impro
Automatic recognition of compressed speech in such applications as voice mail or call centers has significantly degraded performance compared to non-compressed data when background noise is present. Recognition of transmitted speech, such as in cellular, voice over IP, or networked PDA input, may also face the problem of frame erasures. There have been various attempts to compensate for these t...
متن کاملStudies on Error Control of 3-d Zerotree Wavelet Video Streaming
With the increasing popularity of digital video communications over packet switching networks such as the Internet and wireless networks, error control techniques have become a critical research area. Due to its excellent scalability and performance, embedded 3-D zerotree wavelet video compression has great potential in nonconversational scalable video streaming applications. Although error con...
متن کامل