This paper presents an overview and evaluation of some of the end-to-end ASR models on long-form audios. We study three categories of Automatic Speech Recognition(ASR) models based on their core architecture: (1) convolutional, (2) convolutional with squeeze-and-excitation and (3) convolutional models with attention. We selected one ASR model from each category and evaluated Word Error Rate, maximum audio length and real-time factor for each model on a variety of long audio benchmarks: Earnings-21 and 22, CORAAL, and TED-LIUM3. The model from the category of self-attention with local attention and global token has the best accuracy comparing to other architectures. We also compared models with CTC and RNNT decoders and showed that CTC-based models are more robust and efficient than RNNT on long form audio.

翻译：本文概述并评估了部分端到端ASR模型在长音频上的性能。我们基于核心架构将自动语音识别（ASR）模型分为三类进行研究：（1）卷积模型，（2）带挤压激励的卷积模型，（3）带注意力的卷积模型。我们从每类中选取一个ASR模型，在多个长音频基准（Earnings-21和22、CORAAL、TED-LIUM3）上评估其词错误率、最大音频长度和实时因子。实验表明，采用局部注意力与全局令牌的自注意力模型在精度上优于其他架构。我们还比较了采用CTC与RNNT解码器的模型，结果表明基于CTC的模型在长音频上比RNNT更具鲁棒性和高效性。