Related papers: Incremental Learning for End-to-End Automatic Spee…
Training a code-switching end-to-end automatic speech recognition (ASR) model normally requires a large amount of data, while code-switching data is often limited. In this paper, three novel approaches are proposed for code-switching data…
Most meta-learning approaches assume the existence of a very large set of labeled data available for episodic meta-learning of base knowledge. This contrasts with the more realistic continual learning paradigm in which data arrives…
We present a Conformer-based end-to-end neural diarization (EEND) model that uses both acoustic input and features derived from an automatic speech recognition (ASR) model. Two categories of features are explored: features derived directly…
Although automatic speech recognition (ASR) task has gained remarkable success by sequence-to-sequence models, there are two main mismatches between its training and testing that might lead to performance degradation: 1) The typically used…
End-to-end training of Spoken Language Models (SLMs) commonly involves adapting pre-trained text-based Large Language Models (LLMs) to the speech modality through multi-stage training on diverse tasks such as ASR, TTS and spoken question…
Speech separation has been successfully applied as a frontend processing module of conversation transcription systems thanks to its ability to handle overlapped speech and its flexibility to combine with downstream tasks such as automatic…
Self-attention networks (SAN) have been introduced into automatic speech recognition (ASR) and achieved state-of-the-art performance owing to its superior ability in capturing long term dependency. One of the key ingredients is the…
Automatic speech recognition (ASR) models with low-footprint are increasingly being deployed on edge devices for conversational agents, which enhances privacy. We study the problem of federated continual incremental learning for recurrent…
We present a novel approach to end-to-end automatic speech recognition (ASR) that utilizes pre-trained masked language models (LMs) to facilitate the extraction of linguistic information. The proposed models, BERT-CTC and BECTRA, are…
The ability to learn from incrementally arriving data is essential for any life-long learning system. However, standard deep neural networks forget the knowledge about the old tasks, a phenomenon called catastrophic forgetting, when trained…
In end-to-end automatic speech recognition system, one of the difficulties for language expansion is the limited paired speech and text training data. In this paper, we propose a novel method to generate augmented samples with unpaired…
This paper presents a method to train end-to-end automatic speech recognition (ASR) models using unpaired data. Although the end-to-end approach can eliminate the need for expert knowledge such as pronunciation dictionaries to build ASR…
Transfer learning from high-resource languages is known to be an efficient way to improve end-to-end automatic speech recognition (ASR) for low-resource languages. Pre-trained or jointly trained encoder-decoder models, however, do not share…
Incremental learning enables artificial agents to learn from sequential data. While important progress was made by exploiting deep neural networks, incremental learning remains very challenging. This is particularly the case when no memory…
End-to-end models have gradually become the preferred option for automatic speech recognition (ASR) applications. During the training of end-to-end ASR, data augmentation is a quite effective technique for regularizing the neural networks.…
Sequence-to-sequence automatic speech recognition (ASR) models require large quantities of data to attain high performance. For this reason, there has been a recent surge in interest for unsupervised and semi-supervised training in such…
We previously proposed contextual spelling correction (CSC) to correct the output of end-to-end (E2E) automatic speech recognition (ASR) models with contextual information such as name, place, etc. Although CSC has achieved reasonable…
Sequence-to-sequence attention-based models integrate an acoustic, pronunciation and language model into a single neural network, which make them very suitable for multilingual automatic speech recognition (ASR). In this paper, we are…
The main purpose of incremental learning is to learn new knowledge while not forgetting the knowledge which have been learned before. At present, the main challenge in this area is the catastrophe forgetting, namely the network will lose…
End-to-end intent classification using speech has numerous advantages compared to the conventional pipeline approach using automatic speech recognition (ASR), followed by natural language processing modules. It attempts to predict intent…