The rapidly evolving field of artificial intelligence (AI) continues to witness the introduction of
innovative open-source pre-trained models, fostering advancements in various applications …

Automatic Speech Recognition (ASR) has seen remarkable advancements with deep neural
networks, such as Transformer and Conformer. However, these models typically have large …

In this paper, we propose to develop a method to address unsupervised domain adaptation
(UDA) in a practical setting of continual learning (CL). The goal is to update the model on …

In this paper, we propose to develop a method to address unsupervised domain adaptation
(UDA) in a practical setting of continual learning (CL). The goal is to update the model on …

This paper explores the improvement of post-training quantization (PTQ) after knowledge
distillation in the Whisper speech foundation model family. We address the challenge of …

We propose a novel one-pass multiple ASR systems joint compression and quantization
approach using an all-in-one neural model. A single compression cycle allows multiple …

Self-Supervised Learning (SSL) has allowed leveraging large amounts of unlabeled speech
data to improve the performance of speech recognition models even with small annotated …

Automatic speech recognition (ASR) systems have emerged as indispensable tools across a
wide spectrum of applications, ranging from transcription services to voice-activated …

Continued self-supervised (SSL) pre-training for adapting existing SSL models to the target
domain has shown to be extremely effective for low-resource Automatic Speech Recognition …

Recent advancements in automatic speech recognition such as Wav2vec 2.0 and Whisper,
confront deployment challenges due to their substantial model parameters. Model …