Speech-Centric Information Processing: An Optimization-Oriented Approach

Xiaodong He, Li Deng

Proceedings of the IEEE · 2013 · 44 citations · 92 references

DOIFull text

Open access

Concepts

TL;DR

Automatic speech recognition is a core component of voice‑driven systems, and integrating it with downstream tasks such as translation, understanding, and retrieval presents both challenges and opportunities for optimal system design. The paper proposes an optimization‑oriented statistical framework for end‑to‑end speech‑centric information processing, reviews prior work, and outlines future challenges and opportunities. The framework incorporates subsystem interactions and aligns optimization objectives with system performance, applying techniques that optimize decoding and learning phases while marginalizing speech‑recognition uncertainty. The paper also surveys existing research in the area.

Abstract

Automatic speech recognition (ASR) is a central and common component of voice-driven information processing systems in human language technology, including spoken language translation (SLT), spoken language understanding (SLU), voice search, spoken document retrieval, and so on. Interfacing ASR with its downstream text-based processing tasks of translation, understanding, and information retrieval (IR) creates both challenges and opportunities in optimal design of the combined, speech-enabled systems. We present an optimization-oriented statistical framework for the overall system design where the interactions between the subsystems in tandem are fully incorporated and where design consistency is established between the optimization objectives and the end-to-end system performance metrics. Techniques for optimizing such objectives in both the decoding and learning phases of the speech-centric information processing (SCIP) system design are described, in which the uncertainty in speech recognition subsystem's outputs is fully considered and marginalized. This paper provides an overview of the past and current work in this area. Future challenges and new opportunities are also discussed and analyzed.

References

92