Related papers: Adaptive Multi-Corpora Language Model Training for…

Recurrent neural networks (RNNs), especially long short-term memory (LSTM) RNNs, are effective network for sequential task like speech recognition. Deeper LSTM models perform well on large vocabulary continuous speech recognition, because…

Real-world machine learning applications often struggle with two major challenges: distribution shift and label noise. Models tend to overfit by focusing on redundant and uninformative features in the training data, which makes it hard for…

Word-level sign language recognition (WSLR) has attracted attention because it is expected to overcome the communication barrier between people with speech impairment and those who can hear. In the WSLR problem, a method designed for action…

Automatic Speech Recognition (ASR) models have achieved remarkable accuracy in general settings, yet their performance often degrades in domain-specific applications due to data mismatch and linguistic variability. This challenge is…

Neural network language models (NNLMs) have achieved ever-improving accuracy due to more sophisticated architectures and increasing amounts of training data. However, the inductive bias of these models (formed by the distributional…

Neural sequence-to-sequence automatic speech recognition (ASR) systems are in principle open vocabulary systems, when using appropriate modeling units. In practice, however, they often fail to recognize words not seen during training, e.g.,…

Negative transfer in training of acoustic models for automatic speech recognition has been reported in several contexts such as domain change or speaker characteristics. This paper proposes a novel technique to overcome negative transfer by…

End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these…

This paper presents methods to accelerate recurrent neural network based language models (RNNLMs) for online speech recognition systems. Firstly, a lossy compression of the past hidden layer outputs (history vector) with caching is…

The remarkable success of Large Language Models (LLMs) relies heavily on their substantial scale, which poses significant challenges during model deployment in terms of latency and memory consumption. Recently, numerous studies have…

We propose a method to transfer knowledge across neural machine translation (NMT) models by means of a shared dynamic vocabulary. Our approach allows to extend an initial model for a given language pair to cover new languages by adapting…

Spoken Language Models (SLMs) are increasingly central to modern speech-driven applications, but performance degrades under acoustic shift - real-world noise, reverberation, and microphone variation. Prior solutions rely on offline domain…

Data-driven subword segmentation has become the default strategy for open-vocabulary machine translation and other NLP tasks, but may not be sufficiently generic for optimal learning of non-concatenative morphology. We design a test suite…

We propose a new meta learning based framework for low resource speech recognition that improves the previous model agnostic meta learning (MAML) approach. The MAML is a simple yet powerful meta learning approach. However, the MAML presents…

Through the development of neural machine translation, the quality of machine translation systems has been improved significantly. By exploiting advancements in deep learning, systems are now able to better approximate the complex mapping…

The prevalence of the powerful multilingual models, such as Whisper, has significantly advanced the researches on speech recognition. However, these models often struggle with handling the code-switching setting, which is essential in…

We present a novel adaptive random subspace learning algorithm (RSSL) for prediction purpose. This new framework is flexible where it can be adapted with any learning technique. In this paper, we tested the algorithm for regression and…

Recent speech foundation models excel at multilingual automatic speech recognition (ASR) for high-resource languages, but adapting them to low-resource languages remains challenging due to data scarcity and efficiency constraints.…

The success of Vision Language Models (VLMs) on various vision-language tasks heavily relies on pre-training with large scale web-crawled datasets. However, the noisy and incomplete nature of web data makes dataset scale crucial for…

In automatic speech recognition (ASR), model pruning is a widely adopted technique that reduces model size and latency to deploy neural network models on edge devices with resource constraints. However, multiple models with different…