相关论文: SMILE: Speech Meta In-Context Learning for Low-Res…

Languages usually switch within a multilingual speech signal, especially in a bilingual society. This phenomenon is referred to as code-switching (CS), making automatic speech recognition (ASR) challenging under a multilingual scenario. We…

Self-supervised learning (SSL) leverages large amounts of unlabelled data to learn rich speech representations, fostering improvements in automatic speech recognition (ASR), even when only a small amount of labelled data is available for…

Automatic speech recognition (ASR) for African languages remains constrained by limited labeled data and the lack of systematic guidance on model selection, data scaling, and decoding strategies. Large pre-trained systems such as Whisper,…

Automatic Speech Recognition (ASR) technologies have transformed human-computer interaction; however, low-resource languages in Africa remain significantly underrepresented in both research and practical applications. This study…

Children's automatic speech recognition (ASR) is always difficult due to, in part, the data scarcity problem, especially for kindergarten-aged kids. When data are scarce, the model might overfit to the training data, and hence good starting…

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,…

In this paper, we propose an incremental learning method for end-to-end Automatic Speech Recognition (ASR) which enables an ASR system to perform well on new tasks while maintaining the performance on its originally learned ones. To…

Exploiting cross-lingual resources is an effective way to compensate for data scarcity of low resource languages. Recently, a novel multilingual model fusion technique has been proposed where a model is trained to learn cross-lingual…

Automatic Speech Recognition (ASR) aims to convert human speech content into corresponding text. In conversational scenarios, effectively utilizing context can enhance its accuracy. Large Language Models' (LLMs) exceptional long-context…

Deep model training on extensive datasets is increasingly becoming cost-prohibitive, prompting the widespread adoption of deep model fusion techniques to leverage knowledge from pre-existing models. From simple weight averaging to more…

Cross-lingual Speech Emotion Recognition (CLSER) aims to identify emotional states in unseen languages. However, existing methods heavily rely on the semantic synchrony of complete labels and static feature stability, hindering low-resource…

Contextual biasing improves automatic speech recognition (ASR) by integrating external knowledge, such as user-specific phrases or entities, during decoding. In this work, we use an attention-based biasing decoder to produce scores for…

While automatic speech recognition (ASR) systems degrade significantly in noisy environments, audio-visual speech recognition (AVSR) systems aim to complement the audio stream with noise-invariant visual cues and improve the system's…

Automatic Speech Recognition (ASR) has witnessed a profound research interest. Recent breakthroughs have given ASR systems different prospects such as faithfully transcribing spoken language, which is a pivotal advancement in building…

Large language model (LLM)-based automatic speech recognition (ASR) has recently achieved strong performance across diverse tasks, yet contextual biasing for named entities and hotwords under large vocabularies remains challenging. In this…

Although multilingual automatic speech recognition (ASR) systems have significantly advanced, enabling a single model to handle multiple languages, inherent linguistic differences and data imbalances challenge SOTA performance across all…

There exist three approaches for multilingual and crosslingual automatic speech recognition (MCL-ASR) - supervised pretraining with phonetic or graphemic transcription, and self-supervised pretraining. We find that pretraining with phonetic…

Conventional end-to-end automatic speech recognition (ASR) systems rely on paired speech-text data for domain adaptation. Recent LLM-based ASR architectures connect a speech encoder to a large language model via a projection module,…

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.…

A non-parametric low-resolution face recognition model for resource-constrained environments with limited networking and computing is proposed in this work. Such environments often demand a small model capable of being effectively trained…