相关论文: Incremental Layer-wise Self-Supervised Learning fo…

While deep learning based end-to-end automatic speech recognition (ASR) systems have greatly simplified modeling pipelines, they suffer from the data sparsity issue. In this work, we propose a self-training method with an end-to-end system…

Accent variability has posed a huge challenge to automatic speech recognition~(ASR) modeling. Although one-hot accent vector based adaptation systems are commonly used, they require prior knowledge about the target accent and cannot handle…

The success of the multilingual automatic speech recognition systems empowered many voice-driven applications. However, measuring the performance of such systems remains a major challenge, due to its dependency on manually transcribed…

The advent of Large Language Models (LLM) has reformed the Automatic Speech Recognition (ASR). Prompting LLM with audio embeddings to generate transcriptions becomes the new state-of-the-art ASR. Despite LLMs being trained with an extensive…

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…

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…

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…

Speech model adaptation is crucial to handle the discrepancy between server-side proxy training data and actual data received on local devices of users. With the use of federated learning (FL), we introduce an efficient approach on…

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…

While current state-of-the-art Automatic Speech Recognition (ASR) systems achieve high accuracy on typical speech, they suffer from significant performance degradation on disordered speech and other atypical speech patterns. Personalization…

Data-driven models achieve successful results in Speech Emotion Recognition (SER). However, these models, which are often based on general acoustic features or end-to-end approaches, show poor performance when the testing set has a…

This paper introduces a lightweight deep learning model for real-time speech enhancement, designed to operate efficiently on resource-constrained devices. The proposed model leverages a compact architecture that facilitates rapid inference…

Edge-based automatic speech recognition (ASR) technologies are increasingly prevalent in the development of intelligent and personalized assistants. However, resource-constrained ASR models face significant challenges in adaptivity,…

Sequence-to-sequence attention-based models on subword units allow simple open-vocabulary end-to-end speech recognition. In this work, we show that such models can achieve competitive results on the Switchboard 300h and LibriSpeech 1000h…

In Automatic Speech Recognition (ASR), teacher-student (T/S) training has shown to perform well for domain adaptation with small amount of training data. However, adaption without ground-truth labels is still challenging. A previous study…

Transformer-based self-supervised models are trained as feature extractors and have empowered many downstream speech tasks to achieve state-of-the-art performance. However, both the training and inference process of these models may…

In automatic speech recognition, any factor that alters the acoustic properties of speech can pose a challenge to the system's performance. This paper presents a novel approach for automatic whispered speech recognition in the Irish dialect…

Sequence-to-sequence models, such as attention-based models in automatic speech recognition (ASR), are typically trained to optimize the cross-entropy criterion which corresponds to improving the log-likelihood of the data. However, system…

Self- and semi-supervised learning methods have been actively investigated to reduce labeled training data or enhance the model performance. However, the approach mostly focus on in-domain performance for public datasets. In this study, we…

With increasingly more powerful compute capabilities and resources in today's devices, traditionally compute-intensive automatic speech recognition (ASR) has been moving from the cloud to devices to better protect user privacy. However, it…