Related papers: Continual learning using lattice-free MMI for spee…

Automatic speech recognition (ASR) models are typically trained on large datasets of transcribed speech. As language evolves and new terms come into use, these models can become outdated and stale. In the context of models trained on the…

We investigate how agents built on pretrained large language models (LLMs) can learn target classification functions from labeled examples without parameter updates. While conventional approaches like fine-tuning are often costly,…

The continual learning (CL) paradigm aims to enable neural networks to learn tasks continually in a sequential fashion. The fundamental challenge in this learning paradigm is catastrophic forgetting previously learned tasks when the model…

Maximum mutual information (MMI) has become one of the two de facto methods for sequence-level training of speech recognition acoustic models. This paper aims to isolate, identify and bring forward the implicit modelling decisions induced…

In this technical report, we empirically investigate the relationship between linguistic fluency and domain knowledge in the context of continual learning with large language models (LLMs). Specifically, we enhance the linguistic fluency of…

Continual learning has gained increasing importance as it facilitates the acquisition and refinement of scalable knowledge and skills in language models. However, existing methods typically encounter strict limitations and challenges in…

This paper investigates discrete and continuous speech representations in Large Language Model (LLM)-based Automatic Speech Recognition (ASR), organizing them by feature continuity and training approach into four categories: supervised and…

Instruction tuning is now a widely adopted approach to aligning large multimodal models (LMMs) to follow human intent. It unifies the data format of vision-language tasks, enabling multi-task joint training. However, vision-language tasks…

Goal: Numerous studies had successfully differentiated normal and abnormal voice samples. Nevertheless, further classification had rarely been attempted. This study proposes a novel approach, using continuous Mandarin speech instead of a…

Continual Learning (CL) on time series data represents a promising but under-studied avenue for real-world applications. We propose two new CL benchmarks for Human State Monitoring. We carefully designed the benchmarks to mirror real-world…

Neural language modeling (LM) has led to significant improvements in several applications, including Automatic Speech Recognition. However, they typically require large amounts of training data, which is not available for many domains and…

Trans-dimensional random field language models (TRF LMs) where sentences are modeled as a collection of random fields, have shown close performance with LSTM LMs in speech recognition and are computationally more efficient in inference.…

Cognitive functions in current artificial intelligence networks are tied to the exponential increase in network scale, whereas the human brain can continuously learn hundreds of cognitive functions with remarkably low energy consumption.…

Task-free continual learning (CL) aims to learn a non-stationary data stream without explicit task definitions and not forget previous knowledge. The widely adopted memory replay approach could gradually become less effective for long data…

While biological intelligence grows organically as new knowledge is gathered throughout life, Artificial Neural Networks forget catastrophically whenever they face a changing training data distribution. Rehearsal-based Continual Learning…

A common challenge in continual learning (CL) is catastrophic forgetting, where the performance on old tasks drops after new, additional tasks are learned. In this paper, we propose a novel framework called ReCL to slow down forgetting in…

Noise-robust automatic speech recognition (ASR) has been commonly addressed by applying speech enhancement (SE) at the waveform level before recognition. However, speech-level enhancement does not always translate into consistent…

While there has been substantial amount of work in speaker diarization recently, there are few efforts in jointly employing lexical and acoustic information for speaker segmentation. Towards that, we investigate a speaker diarization system…

Estimating time-frequency domain masks for single-channel speech enhancement using deep learning methods has recently become a popular research field with promising results. In this paper, we propose a novel components loss (CL) for the…

Large Language Models (LLMs) exhibit strong general language capabilities. However, fine-tuning these models on domain-specific tasks often leads to catastrophic forgetting, where the model overwrites or loses essential knowledge acquired…