相关论文: DARTS-ASR: Differentiable Architecture Search for …

Low-resource automatic speech recognition (ASR) is challenging, as the low-resource target language data cannot well train an ASR model. To solve this issue, meta-learning formulates ASR for each source language into many small ASR tasks…

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 performance of voice-controlled systems is usually influenced by accented speech. To make these systems more robust, the frontend accent recognition (AR) technologies have received increased attention in recent years. As accent is a…

The pervasiveness of intra-utterance code-switching (CS) in spoken content requires that speech recognition (ASR) systems handle mixed language. Designing a CS-ASR system has many challenges, mainly due to data scarcity, grammatical…

We present a Model Uncertainty-aware Differentiable ARchiTecture Search ($\mu$DARTS) that optimizes neural networks to simultaneously achieve high accuracy and low uncertainty. We introduce concrete dropout within DARTS cells and include a…

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…

The prevalence of the powerful multilingual models, such as Whisper, has significantly advanced the researches on speech recognition. However, these models often struggle with handling the code-switching setting, which is essential in…

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,…

The end-to-end ASR model is often desired in the streaming multilingual scenario since it is easier to deploy and can benefit from pre-trained speech models such as powerful foundation models. Meanwhile, the heterogeneous nature and…

End-to-end automatic speech recognition (ASR) systems are increasingly popular due to their relative architectural simplicity and competitive performance. However, even though the average accuracy of these systems may be high, the…

We propose a bottom-up framework for automatic speech recognition (ASR) in syllable-based languages by unifying language-universal articulatory attribute modeling with syllable-level prediction. The system first recognizes sequences or…

Towards developing high-performing ASR for low-resource languages, approaches to address the lack of resources are to make use of data from multiple languages, and to augment the training data by creating acoustic variations. In this work…

Automatic Speech Recognition (ASR) systems frequently use a search-based decoding strategy aiming to find the best attainable transcript by considering multiple candidates. One prominent speech recognition decoding heuristic is beam search,…

Automatic recognition of disordered and elderly speech remains highly challenging tasks to date due to data scarcity. Parameter fine-tuning is often used to exploit the large quantities of non-aged and healthy speech pre-trained models,…

We propose a novel end-to-end multi-talker automatic speech recognition (ASR) framework that enables both multi-speaker (MS) ASR and target-speaker (TS) ASR. Our proposed model is trained in a fully end-to-end manner, incorporating speaker…

We study device-addressed speech detection under pre-ASR edge deployment constraints, where systems must decide whether to forward audio before transcription under strict latency and compute limits. We show that, in multi-speaker…

Neural architecture search (NAS) has shown great promise in the field of automated machine learning (AutoML). NAS has outperformed hand-designed networks and made a significant step forward in the field of automating the design of deep…

Building an automatic speech recognition (ASR) system from scratch requires a large amount of annotated speech data, which is difficult to collect in many languages. However, there are cases where the low-resource language shares a common…

Conventional research on speech recognition modeling relies on the canonical form for most low-resource languages while automatic speech recognition (ASR) for regional dialects is treated as a fine-tuning task. To investigate the effects of…

This paper presents a novel deep learning architecture for acoustic model in the context of Automatic Speech Recognition (ASR), termed as MixNet. Besides the conventional layers, such as fully connected layers in DNN-HMM and memory cells in…