连续语音识别中的统计建模(CSR)(特邀报告)
Statistical Modeling in Continuous Speech Recognition (CSR)(Invited Talk)
摘要:
自动连续语音识别(CSR)已经足够成熟,现在可以实现各种现实世界的应用,包括大词汇量的转录和交互式口语对话。本文回顾了统计建模技术的演变,这些技术是当今系统的基础,特别是隐马尔可夫模型(HMM)和N-gram。从描述的语音信号和它的参数化,各种建模假设和它们的后果进行了讨论。然后,它描述了各种技术,这些假设的影响可以减轻。尽管已经取得了进展,目前的建模技术的局限性仍然是显而易见的。因此,本文最后简要回顾了一些更基本的建模工作正在进行中。
英文摘要:
Automatic continuous speech recognition (CSR) is sufficiently mature that a variety of real world applications are now possible including large vocabulary transcription and interactive spoken dialogues. This paper reviews the evolution of the statistical modelling techniques which underlie current-day systems, specifically hidden Markov models (HMMs) and N-grams. Starting from a description of the speech signal and its parameterisation, the various modelling assumptions and their consequences are discussed. It then describes various techniques by which the effects of these assumptions can be mitigated. Despite the progress that has been made, the limitations of current modelling techniques are still evident. The paper therefore concludes with a brief review of some of the more fundamental modelling work now in progress.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。