Related papers: Incorporating L2 Phonemes Using Articulatory Featu…

Recognition of uncommon words such as names and technical terminology is important to understanding conversations in context. However, the ability to recognise such words remains a challenge in modern automatic speech recognition (ASR)…

Multi-speaker automatic speech recognition (MS-ASR) faces significant challenges in transcribing overlapped speech, a task critical for applications like meeting transcription and conversational analysis. While serialized output training…

The disparity in phonology between learner's native (L1) and target (L2) language poses a significant challenge for mispronunciation detection and diagnosis (MDD) systems. This challenge is further intensified by lack of annotated L2 data.…

Due to the recent advances of natural language processing, several works have applied the pre-trained masked language model (MLM) of BERT to the post-correction of speech recognition. However, existing pre-trained models only consider the…

Developing a practical speech recognizer for a low resource language is challenging, not only because of the (potentially unknown) properties of the language, but also because test data may not be from the same domain as the available…

Multimodal large language models (MLLMs) have recently become a focal point of research due to their formidable multimodal understanding capabilities. For example, in the audio and speech domains, an LLM can be equipped with (automatic)…

In this paper, we propose a language-universal adapter learning framework based on a pre-trained model for end-to-end multilingual automatic speech recognition (ASR). For acoustic modeling, the wav2vec 2.0 pre-trained model is fine-tuned by…

In this paper, we investigate the usage of large language models (LLMs) to improve the performance of competitive speech recognition systems. Different from previous LLM-based ASR error correction methods, we propose a novel multi-stage…

Automatic speech recognition (ASR) technologies have been significantly advanced in the past few decades. However, recognition of overlapped speech remains a highly challenging task to date. To this end, multi-channel microphone array data…

End-to-end automatic speech recognition (E2E-ASR) has the potential to improve performance, but a specific issue that needs to be addressed is the difficulty it has in handling enharmonic words: named entities (NEs) with the same…

Large Language Model (LLM)-powered Automatic Speech Recognition (ASR) systems achieve strong performance with limited resources by linking a frozen speech encoder to a pretrained LLM via a lightweight connector. Prior work trains a separate…

End-to-end (E2E) systems have played a more and more important role in automatic speech recognition (ASR) and achieved great performance. However, E2E systems recognize output word sequences directly with the input acoustic feature, which…

This paper investigates sequence-to-sequence Transformer models for automatic speech recognition (ASR) error correction in low-resource Burmese, focusing on different feature integration strategies including IPA and alignment information.…

In this paper, we start by training End-to-End Automatic Speech Recognition (ASR) models using Federated Learning (FL) and examining the fundamental considerations that can be pivotal in minimizing the performance gap in terms of word error…

Automatic speech recognition (ASR) for conversational code-switching speech remains challenging due to the scarcity of realistic, high-quality labeled speech data. This paper explores multilingual text-to-speech (TTS) models as an effective…

Most of the previous approaches to lyrics-to-audio alignment used a pre-developed automatic speech recognition (ASR) system that innately suffered from several difficulties to adapt the speech model to individual singers. A significant…

Recent advances in automatic speech recognition (ASR) have combined speech encoders with large language models (LLMs) through projection, forming Speech LLMs with strong performance. However, adapting them to new domains remains…

Recent advancements in deep learning have significantly enhanced multilingual automatic speech recognition (ASR) due to the development of advanced model architectures and available large-scale multilingual datasets. Despite that,…

Humans are capable of processing speech by making use of multiple sensory modalities. For example, the environment where a conversation takes place generally provides semantic and/or acoustic context that helps us to resolve ambiguities or…

Most end-to-end (E2E) speech recognition models are composed of encoder and decoder blocks that perform acoustic and language modeling functions. Pretrained large language models (LLMs) have the potential to improve the performance of E2E…