Related papers: A Unified Speaker Adaptation Approach for ASR

Speaker-attributed automatic speech recognition (SA-ASR) aims to transcribe speech while assigning transcripts to the corresponding speakers accurately. Existing methods often rely on complex modular systems or require extensive fine-tuning…

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…

Automatic speech recognition (ASR) models are typically designed to operate on a single input data type, e.g. a single or multi-channel audio streamed from a device. This design decision assumes the primary input data source does not change…

In the realm of automatic speech recognition (ASR), robustness in noisy environments remains a significant challenge. Recent ASR models, such as Whisper, have shown promise, but their efficacy in noisy conditions can be further enhanced.…

Cross-lingual speech adaptation aims to solve the problem of leveraging multiple rich-resource languages to build models for a low-resource target language. Since the low-resource language has limited training data, speech recognition…

In this work, we introduce a simple yet efficient post-processing model for automatic speech recognition (ASR). Our model has Transformer-based encoder-decoder architecture which "translates" ASR model output into grammatically and…

In previous work, we developed a closed-loop speech chain model based on deep learning, in which the architecture enabled the automatic speech recognition (ASR) and text-to-speech synthesis (TTS) components to mutually improve their…

Edge-based automatic speech recognition (ASR) technologies are increasingly prevalent in the development of intelligent and personalized assistants. However, resource-constrained ASR models face significant challenges in adaptivity,…

One-shot style transfer is a challenging task, since training on one utterance makes model extremely easy to over-fit to training data and causes low speaker similarity and lack of expressiveness. In this paper, we build on the…

While Automatic Speech Recognition (ASR) models have shown significant advances with the introduction of unsupervised or self-supervised training techniques, these improvements are still only limited to a subsection of languages and…

Dysarthric speech recognition faces challenges from severity variations and disparities relative to normal speech. Conventional approaches individually fine-tune ASR models pre-trained on normal speech per patient to prevent feature…

In this paper, we present a novel modeling method for single-channel multi-talker overlapped automatic speech recognition (ASR) systems. Fully neural network based end-to-end models have dramatically improved the performance of multi-taker…

This paper explores the use of ASR-pretrained Conformers for speaker verification, leveraging their strengths in modeling speech signals. We introduce three strategies: (1) Transfer learning to initialize the speaker embedding network,…

Speech foundation models have achieved state-of-the-art (SoTA) performance across various tasks, such as automatic speech recognition (ASR) in hundreds of languages. However, multi-speaker ASR remains a challenging task for these models due…

Neural speaker embeddings encode the speaker's speech characteristics through a DNN model and are prevalent for speaker verification tasks. However, few studies have investigated the usage of neural speaker embeddings for an ASR system. In…

Despite recent improvements in End-to-End Automatic Speech Recognition (E2E ASR) systems, the performance can degrade due to vocal characteristic mismatches between training and testing data, particularly with limited target speaker…

Speaker adaptation, which involves cloning voices from unseen speakers in the Text-to-Speech task, has garnered significant interest due to its numerous applications in multi-media fields. Despite recent advancements, existing methods often…

General-purpose ASR underperforms for atypical speakers, such as L2 learners, reinforcing bias and limiting use in education and accessibility. Using the CEFR-graded Speak and Improve corpus, we show that naive fine-tuning of Whisper…

In the past few years, it has been shown that deep learning systems are highly vulnerable under attacks with adversarial examples. Neural-network-based automatic speech recognition (ASR) systems are no exception. Targeted and untargeted…

This study investigates the performance of personalized automatic speech recognition (ASR) for recognizing disordered speech using small amounts of per-speaker adaptation data. We trained personalized models for 195 individuals with…