Although deep learning-based end-to-end Automatic Speech Recognition (ASR)
has shown remarkable performance in recent years, it suffers severe performance
regression on test samples drawn from different data distributions. Test-time
Adaptation (TTA), previously explored in the computer vision area, aims to
adapt the model trained on source domains to yield better predictions for test
samples, often out-of-domain, without accessing the source data. Here, we
propose the Single-Utterance Test-time Adaptation (SUTA) framework for ASR,
which is the first TTA study on ASR to our best knowledge. The single-utterance
TTA is a more realistic setting that does not assume test data are sampled from
identical distribution and does not delay on-demand inference due to
pre-collection for the batch of adaptation data. SUTA consists of unsupervised
objectives with an efficient adaptation strategy. Empirical results demonstrate
that SUTA effectively improves the performance of the source ASR model
evaluated on multiple out-of-domain target corpora and in-domain test samples.

该研究提出了单次话语测试时间自适应（Single-Utterance Test-time Adaptation，SUTA）框架，首次将测试时间自适应（TTA）应用于语音识别，通过无监督目标和高效的适应策略，有效提高源 ASR 模型在多个域外目标语料库和域内测试样本上的性能。

听取、适应、提高 WER：源自由单语音时自适应用于自动语音识别

Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition

Most data is automatically collected and only ever "seen" by algorithms. Yet,
data compressors preserve perceptual fidelity rather than just the information
needed by algorithms performing downstream tasks. In this paper, we
characterize the bit-rate required to ensure high performance on all predictive
tasks that are invariant under a set of transformations, such as data
augmentations. Based on our theory, we design unsupervised objectives for
training neural compressors. Using these objectives, we train a generic image
compressor that achieves substantial rate savings (more than $1000\times$ on
ImageNet) compared to JPEG on 8 datasets, without decreasing downstream
classification performance.

本文利用无监督目标设计神经压缩器进行图像压缩，以满足具有数据增强特征的所有预测任务的高性能，实现了大幅度节省数据率的效果，同时不会降低下游分类性能。

有损压缩用于无损预测

Lossy Compression for Lossless Prediction

Existing neural network architectures in computer vision -- whether designed
by humans or by machines -- were typically found using both images and their
associated labels. In this paper, we ask the question: can we find high-quality
neural architectures using only images, but no human-annotated labels? To
answer this question, we first define a new setup called Unsupervised Neural
Architecture Search (UnNAS). We then conduct two sets of experiments. In
sample-based experiments, we train a large number (500) of diverse
architectures with either supervised or unsupervised objectives, and find that
the architecture rankings produced with and without labels are highly
correlated. In search-based experiments, we run a well-established NAS
algorithm (DARTS) using various unsupervised objectives, and report that the
architectures searched without labels can be competitive to their counterparts
searched with labels. Together, these results reveal the potentially surprising
finding that labels are not necessary, and the image statistics alone may be
sufficient to identify good neural architectures.

本文介绍了一种无监督神经网络搜索机制 (Unsupervised Neural Architecture Search, UnNAS)，通过对 500 个不同网络结构的有监督或无监督目标进行训练，发现使用图像统计数据替代人类注释标签的效果与实际人类标签高度相关，并且这种方式可以用于搜索高质量的神经网络架构。