Recent advances in speech recognition and translation rely on hundreds of
thousands of hours of Internet speech data. We argue that state-of-the art
accuracy can be reached without relying on web-scale data. Canary -
multilingual ASR and speech translation model, outperforms current
state-of-the-art models - Whisper, OWSM, and Seamless-M4T on English, French,
Spanish, and German languages, while being trained on an order of magnitude
less data than these models. Three key factors enables such data-efficient
model: (1) a FastConformer-based attention encoder-decoder architecture (2)
training on synthetic data generated with machine translation and (3) advanced
training techniques: data-balancing, dynamic data blending, dynamic bucketing
and noise-robust fine-tuning. The model, weights, and training code will be
open-sourced.

最新的语音识别和翻译技术依赖于数十万小时的互联网语音数据。我们认为即使不依赖于互联网规模的数据，也可以达到最先进的准确性。Canary - 多语言 ASR 和语音翻译模型在英语、法语、西班牙语和德语等语言上优于当前最先进的模型 - Whisper、OWSM 和 Seamless-M4T，与这些模型相比，它使用的数据量更少一个数量级。三个关键因素使得这种数据高效模型成为可能：（1）基于 FastConformer 的注意力编码器 - 解码器架构，（2）使用机器翻译生成的合成数据进行训练，以及（3）先进的训练技术：数据平衡、动态数据融合、动态分桶和抗噪音微调。该模型以及权重和训练代码将开源。

少即是多：准确无需 Web 规模数据的语音识别和翻译

Less is More: Accurate Speech Recognition & Translation without  Web-Scale Data

Event extraction requires high-quality expert human annotations, which are
usually expensive. Therefore, learning a data-efficient event extraction model
that can be trained with only a few labeled examples has become a crucial
challenge. In this paper, we focus on low-resource end-to-end event extraction
and propose DEGREE, a data-efficient model that formulates event extraction as
a conditional generation problem. Given a passage and a manually designed
prompt, DEGREE learns to summarize the events mentioned in the passage into a
natural sentence that follows a predefined pattern. The final event predictions
are then extracted from the generated sentence with a deterministic algorithm.
DEGREE has three advantages to learn well with less training data. First, our
designed prompts provide semantic guidance for DEGREE to leverage DEGREE and
thus better capture the event arguments. Moreover, DEGREE is capable of using
additional weakly-supervised information, such as the description of events
encoded in the prompts. Finally, DEGREE learns triggers and arguments jointly
in an end-to-end manner, which encourages the model to better utilize the
shared knowledge and dependencies among them. Our experimental results
demonstrate the strong performance of DEGREE for low-resource event extraction.

文章提出了一种数据有效性事件提取模型 DEGREE，通过联合学习触发器和参数，利用设计的提示语义指导模型，能够在少量有标注数据的情况下进行低资源端到端的事件提取，并从生成的自然语言摘要中提取最终事件预测结果。