Recent end-to-end automatic speech recognition (ASR) models have become
increasingly larger, making them particularly challenging to be deployed on
resource-constrained devices. Model quantisation is an effective solution that
sometimes causes the word error rate (WER) to increase. In this paper, a novel
strategy of personalisation for a quantised model (PQM) is proposed, which
combines speaker adaptive training (SAT) with model quantisation to improve the
performance of heavily compressed models. Specifically, PQM uses a 4-bit
NormalFloat Quantisation (NF4) approach for model quantisation and low-rank
adaptation (LoRA) for SAT. Experiments have been performed on the LibriSpeech
and the TED-LIUM 3 corpora. Remarkably, with a 7x reduction in model size and
1% additional speaker-specific parameters, 15.1% and 23.3% relative WER
reductions were achieved on quantised Whisper and Conformer-based
attention-based encoder-decoder ASR models respectively, comparing to the
original full precision models.

使用 4-bit 正态浮点数量化和低秩自适应方法相结合的个性化量化模型策略，大幅降低了模型大小并显著减少了词错误率。

加强量化的端到端 ASR 模型通过个性化

Enhancing Quantised End-to-End ASR Models via Personalisation

Disordered speech recognition is a highly challenging task. The underlying
neuro-motor conditions of people with speech disorders, often compounded with
co-occurring physical disabilities, lead to the difficulty in collecting large
quantities of speech required for system development. This paper investigates a
set of data augmentation techniques for disordered speech recognition,
including vocal tract length perturbation (VTLP), tempo perturbation and speed
perturbation. Both normal and disordered speech were exploited in the
augmentation process. Variability among impaired speakers in both the original
and augmented data was modeled using learning hidden unit contributions (LHUC)
based speaker adaptive training. The final speaker adapted system constructed
using the UASpeech corpus and the best augmentation approach based on speed
perturbation produced up to 2.92% absolute (9.3% relative) word error rate
(WER) reduction over the baseline system without data augmentation, and gave an
overall WER of 26.37% on the test set containing 16 dysarthric speakers.

本文研究了一组用于混乱语音识别的数据增强技术，包括声道长度扰动（VTLP）、节奏扰动和速度扰动，并利用正常和混乱语音进行增强处理。通过基于学习隐藏单元贡献（LHUC）的说话者自适应训练对原始和增强数据中的受损说话者之间的变异性进行建模。使用基于速度扰动的最佳增强方法构建的最终说话者自适应系统相对于没有数据增强的基线系统减少了 2.92％绝对（9.3％相对）的词错误率（WER），并在包含 16 位 Dysarthria 患者的测试集上获得了 26.37％的整体 WER。

探究无序语音识别数据增强技术

Investigation of Data Augmentation Techniques for Disordered Speech Recognition

This work presents a broad study on the adaptation of neural network acoustic
models by means of learning hidden unit contributions (LHUC) -- a method that
linearly re-combines hidden units in a speaker- or environment-dependent manner
using small amounts of unsupervised adaptation data. We also extend LHUC to a
speaker adaptive training (SAT) framework that leads to a more adaptable DNN
acoustic model, working both in a speaker-dependent and a speaker-independent
manner, without the requirements to maintain auxiliary speaker-dependent
feature extractors or to introduce significant speaker-dependent changes to the
DNN structure. Through a series of experiments on four different speech
recognition benchmarks (TED talks, Switchboard, AMI meetings, and Aurora4)
comprising 270 test speakers, we show that LHUC in both its test-only and SAT
variants results in consistent word error rate reductions ranging from 5% to
23% relative depending on the task and the degree of mismatch between training
and test data. In addition, we have investigated the effect of the amount of
adaptation data per speaker, the quality of unsupervised adaptation targets,
the complementarity to other adaptation techniques, one-shot adaptation, and an
extension to adapting DNNs trained in a sequence discriminative manner.

通过学习隐藏单元贡献的调整方法（LHUC），这项工作介绍了神经网络声学模型的适应性研究，将其扩展到发言人自适应训练和多种语音识别基准，并证明在测试和 SAT 方案中，LHUC 均能在不同程度的训练和测试数据不匹配的情况下显著提高词错误率。