Related papers: Resource-Efficient Transfer Learning From Speech F…

Neural front-ends are an appealing alternative to traditional, fixed feature extraction pipelines for automatic speech recognition (ASR) systems since they can be directly trained to fit the acoustic model. However, their performance often…

The adaptation of large language models (LLMs) to specialized reasoning tasks is fundamentally constrained by computational resources. Parameter-Efficient Fine-Tuning (PEFT) methods have emerged as a powerful solution, yet the landscape of…

Fine-tuning speech representation models can enhance performance on specific tasks but often compromises their cross-task generalization ability. This degradation is often caused by excessive changes in the representations, making it…

Existing speech emotion recognition (SER) methods commonly suffer from the lack of high-quality large-scale corpus, partly due to the complex, psychological nature of emotion which makes accurate labeling difficult and time consuming.…

With the growing availability of smart devices and cloud services, personal speech assistance systems are increasingly used on a daily basis. Most devices redirect the voice recordings to a central server, which uses them for upgrading the…

Speech enhancement (SE) aims to suppress the additive noise from a noisy speech signal to improve the speech's perceptual quality and intelligibility. However, the over-suppression phenomenon in the enhanced speech might degrade the…

Conventional methods for aggregating layers in fine-tuned self-supervised speech models, such as using the final layer or weighted sum, suffer from information bottlenecks and static feature weighting for all dataset examples. We propose…

Prior works have investigated the use of articulatory features as complementary representations for automatic speech recognition (ASR), but their use was largely confined to shallow acoustic models. In this work, we revisit articulatory…

Fine-tuning pre-trained models for downstream tasks is a widely adopted technique known for its adaptability and reliability across various domains. Despite its conceptual simplicity, fine-tuning entails several troublesome engineering…

While Speech Foundation Models (SFMs) excel in various speech tasks, their performance for low-resource tasks such as child Automatic Speech Recognition (ASR) is hampered by limited pretraining data. To address this, we explore different…

Conventional speech enhancement technique such as beamforming has known benefits for far-field speech recognition. Our own work in frequency-domain multi-channel acoustic modeling has shown additional improvements by training a spatial…

In recent years, Transformer networks have shown remarkable performance in speech recognition tasks. However, their deployment poses challenges due to high computational and storage resource requirements. To address this issue, a…

In the domain of air traffic control (ATC) systems, efforts to train a practical automatic speech recognition (ASR) model always faces the problem of small training samples since the collection and annotation of speech samples are expert-…

Foundation models have revolutionized artificial intelligence by providing robust, versatile architectures pre-trained on large-scale datasets. However, adapting these massive models to specific downstream tasks requires fine-tuning, which…

Despite improvements to the generalization performance of automated speech recognition (ASR) models, specializing ASR models for downstream tasks remains a challenging task, primarily due to reduced data availability (necessitating…

Automatic Speech Recognition (ASR) performance for low-resource languages is still far behind that of higher-resource languages such as English, due to a lack of sufficient labeled data. State-of-the-art methods deploy self-supervised…

Continual learning is an essential capability of human cognition, yet it poses significant challenges for current deep learning models. The primary issue is that new knowledge can interfere with previously learned information, causing the…

There are significant challenges for speaker adaptation in text-to-speech for languages that are not widely spoken or for speakers with accents or dialects that are not well-represented in the training data. To address this issue, we…

Self-supervised learning (SSL) models have shown exceptional capabilities across various speech-processing tasks. Continuous SSL representations are effective but suffer from high computational and storage demands. On the other hand,…

Self-supervised learning representations (SSLR) have resulted in robust features for downstream tasks in many fields. Recently, several SSLRs have shown promising results on automatic speech recognition (ASR) benchmark corpora. However,…