arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.09044eess.AScs.SD
收藏

超越语音:非常长上下文语音识别的实证研究

Beyond the Utterance: An Empirical Study of Very Long Context Speech Recognition

Department of Computer Science, The University Of Sheffield(计算机科学系,谢菲尔德大学)

Robert Flynn, Anton Ragni

AI总结:

本研究通过训练长上下文ASR模型,发现使用更长的上下文可显著提升语音识别性能,验证了长序列处理的可行性。

摘要:

自动语音识别(ASR)模型通常被训练以在单个语音上运行,持续时间通常少于30秒。这一选择部分是由于计算限制,但同时也反映了一个常见的但往往不准确的建模假设,即认为语音是独立同分布的样本。当长格式音频记录可用时,为了与这些系统一起工作,这些记录必须首先被分割成短语音并独立处理。在本研究中,我们表明,由于最近的算法和硬件进步,这不再必要,当前基于注意力的方法可以用于训练在长达一小时的序列上运行的ASR系统。因此,为了更好地理解训练/评估序列长度与性能之间的关系,我们使用10种不同的序列长度(从10秒到1小时)在大规模数据上训练ASR模型。结果表明,使用多达21.8分钟的上下文是有益的,在我们的主要实验中,与短上下文基线相比,性能提高了14.2%。通过修改各种架构组件,我们发现编码位置信息的方法以及模型的宽度/深度是处理长序列时的重要因素。最后,构建了一系列使用合成数据的评估,以帮助分析模型对上下文的使用。从这些结果可以看出,模型正在利用远距离上下文的语音和语言方面。

英文摘要:

Automatic speech recognition (ASR) models are normally trained to operate over single utterances, with a short duration of less than 30 seconds. This choice has been made in part due to computational constraints, but also reflects a common, but often inaccurate, modelling assumption that treats utterances as independent and identically distributed samples. When long-format audio recordings are available, to work with such systems, these recordings must first be segmented into short utterances and processed independently. In this work, we show that due to recent algorithmic and hardware advances, this is no longer necessary, and current attention-based approaches can be used to train ASR systems that operate on sequences of over an hour in length. Therefore, to gain a better understanding of the relationship between the training/evaluation sequence length and performance, we train ASR models on large-scale data using 10 different sequence lengths from 10 seconds up to 1 hour. The results show a benefit from using up to 21.8 minutes of context, with up to a 14.2% relative improvement from a short context baseline in our primary experiments. Through modifying various architectural components, we find that the method of encoding positional information and the model's width/depth are important factors when working with long sequences. Finally, a series of evaluations using synthetic data are constructed to help analyse the model's use of context. From these results, it is clear that both linguistic and acoustic aspects of the distant context are being used by the model.

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。

↑