Related papers: Toward domain-invariant speech recognition via lar…
While recent automatic speech recognition systems achieve remarkable performance when large amounts of adequate, high quality annotated speech data is used for training, the same systems often only achieve an unsatisfactory result for tasks…
Adapting speaker recognition systems to new environments is a widely-used technique to improve a well-performing model learned from large-scale data towards a task-specific small-scale data scenarios. However, previous studies focus on…
In the area of multi-domain speech recognition, research in the past focused on hybrid acoustic models to build cross-domain and domain-invariant speech recognition systems. In this paper, we empirically examine the difference in behavior…
Speech distortions are a long-standing problem that degrades the performance of supervisely trained speech processing models. It is high time that we enhance the robustness of speech processing models to obtain good performance when…
Speech separation seeks to isolate individual speech signals from a multi-talk speech mixture. Despite much progress, a system well-trained on synthetic data often experiences performance degradation on out-of-domain data, such as…
Domain mismatch between training and testing can lead to significant degradation in performance in many machine learning scenarios. Unfortunately, this is not a rare situation for automatic speech recognition deployments in real-world…
In many automatic speech recognition (ASR) tasks, an ideal model has to be applicable over multiple domains. In this paper, we propose to teach an all-rounder with experts in different domains. Concretely, we build a multi-domain acoustic…
We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize…
Model fine-tuning and adaptation have become a common approach for model specialization for downstream tasks or domains. Fine-tuning the entire model or a subset of the parameters using light-weight adaptation has shown considerable success…
This paper introduces a novel application of Test-Time Training (TTT) for Speech Enhancement, addressing the challenges posed by unpredictable noise conditions and domain shifts. This method combines a main speech enhancement task with a…
Unsupervised speech representation learning has shown remarkable success at finding representations that correlate with phonetic structures and improve downstream speech recognition performance. However, most research has been focused on…
In general, the performance of automatic speech recognition (ASR) systems is significantly degraded due to the mismatch between training and test environments. Recently, a deep-learning-based image-to-image translation technique to…
Thanks to the rise of self-supervised learning, automatic speech recognition (ASR) systems now achieve near-human performance on a wide variety of datasets. However, they still lack generalization capability and are not robust to domain…
Continued pre-training of small language models offers a promising path for domain adaptation with limited computational resources. I've investigated this approach within educational domains, evaluating it as a resource-efficient…
When there is a mismatch between the training and test domains, current speech recognition systems show significant performance degradation. Self-training methods, such as noisy student teacher training, can help address this and enable the…
Most real world language problems require learning from heterogenous corpora, raising the problem of learning robust models which generalise well to both similar (in domain) and dissimilar (out of domain) instances to those seen in…
Self-supervised learning (SSL) algorithms have emerged as powerful tools that can leverage large quantities of unlabeled audio data to pre-train robust representations that support strong performance on diverse downstream tasks. Up to now…
Modern automatic speech recognition (ASR) systems need to be robust under acoustic variability arising from environmental, speaker, channel, and recording conditions. Ensuring such robustness to variability is a challenge in modern day…
In real-life applications, the performance of speaker recognition systems always degrades when there is a mismatch between training and evaluation data. Many domain adaptation methods have been successfully used for eliminating the domain…
In this article we propose a novel approach for adapting speaker embeddings to new domains based on adversarial training of neural networks. We apply our embeddings to the task of text-independent speaker verification, a challenging,…