基于音频前缀低秩适配语言模型的推测式语音识别
Speculative Speech Recognition by Audio-Prefixed Low-Rank Adaptation of Language Models
AI总结：
本文提出推测式语音识别（SSR），通过将RNN-Transducer ASR与音频前缀语言模型结合，使识别器能先于音频预测转录补全，实验证明该方法可有效降低ASR延迟。
摘要：
本文探讨推测式语音识别（SSR），我们赋予传统自动语音识别（ASR）推测能力，使识别器能够先于音频运行。我们引入了一种衡量SSR性能的指标，并提出了一种模型，该模型通过将基于RNN-Transducer的ASR系统与音频前缀语言模型（LM）相结合来实现SSR。ASR系统转录正在进行的音频，并将生成的转录文本连同音频相关前缀一起输入LM，由LM推测转录文本的可能补全。我们在多种ASR数据集上进行了实验，结果表明了我们的方法的有效性以及SSR作为降低ASR延迟方法的可行性。
英文摘要：
This paper explores speculative speech recognition (SSR), where we empower conventional automatic speech recognition (ASR) with speculation capabilities, allowing the recognizer to run ahead of audio. We introduce a metric for measuring SSR performance and we propose a model which does SSR by combining a RNN-Transducer-based ASR system with an audio-prefixed language model (LM). The ASR system transcribes ongoing audio and feeds the resulting transcripts, along with an audio-dependent prefix, to the LM, which speculates likely completions for the transcriptions. We experiment with a variety of ASR datasets on which show the efficacy our method and the feasibility of SSR as a method of reducing ASR latency.
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。
