Related papers: Improving Mandarin Speech Recogntion with Block-au…

Vision is often used as a complementary modality for audio speech recognition (ASR), especially in the noisy environment where performance of solo audio modality significantly deteriorates. After combining visual modality, ASR is upgraded…

Improving the accuracy of single-channel automatic speech recognition (ASR) in noisy conditions is challenging. Strong speech enhancement front-ends are available, however, they typically require that the ASR model is retrained to cope with…

The Transformer self-attention network has shown promising performance as an alternative to recurrent neural networks in end-to-end (E2E) automatic speech recognition (ASR) systems. However, Transformer has a drawback in that the entire…

In real-world applications, users often require both translations and transcriptions of speech to enhance their comprehension, particularly in streaming scenarios where incremental generation is necessary. This paper introduces a streaming…

Accent conversion (AC) transforms a non-native speaker's accent into a native accent while maintaining the speaker's voice timbre. In this paper, we propose approaches to improving accent conversion applicability, as well as quality. First…

In recent decades, many studies have suggested that phase information is crucial for speech enhancement (SE), and time-domain single-channel speech enhancement techniques have shown promise in noise suppression and robust automatic speech…

Code-switching in automatic speech recognition (ASR) is an important challenge due to globalization. Recent research in multilingual ASR shows potential improvement over monolingual systems. We study key issues related to multilingual…

This paper presents our latest investigation on end-to-end automatic speech recognition (ASR) for overlapped speech. We propose to train an end-to-end system conditioned on speaker embeddings and further improved by transfer learning from…

In this paper, we propose MixSpeech, a simple yet effective data augmentation method based on mixup for automatic speech recognition (ASR). MixSpeech trains an ASR model by taking a weighted combination of two different speech features…

For most of the attention-based sequence-to-sequence models, the decoder predicts the output sequence conditioned on the entire input sequence processed by the encoder. The asynchronous problem between the encoding and decoding makes these…

This paper presents the use of non-autoregressive (NAR) approaches for joint automatic speech recognition (ASR) and spoken language understanding (SLU) tasks. The proposed NAR systems employ a Conformer encoder that applies connectionist…

This paper proposes a novel non-autoregressive (NAR) block-based Attention Mask Decoder (AMD) that flexibly balances performance-efficiency trade-offs for Conformer ASR systems. AMD performs parallel NAR inference within contiguous blocks…

Automatic pronunciation error detection (APED) plays an important role in the domain of language learning. As for the previous ASR-based APED methods, the decoded results need to be aligned with the target text so that the errors can be…

Self-supervised pretrained models exhibit competitive performance in automatic speech recognition on finetuning, even with limited in-domain supervised data. However, popular pretrained models are not suitable for streaming ASR because they…

Recently, Transformer based models have shown competitive automatic speech recognition (ASR) performance. One key factor in the success of these models is the multi-head attention mechanism. However, for trained models, we have previously…

Improving end-to-end speech recognition by incorporating external text data has been a longstanding research topic. There has been a recent focus on training E2E ASR models that get the performance benefits of external text data without…

Noise robustness is critical when applying automatic speech recognition (ASR) in real-world scenarios. One solution involves the used of speech enhancement (SE) models as the front end of ASR. However, neural network-based (NN-based) SE…

This report describes the submitted system to the In-Car Multi-Channel Automatic Speech Recognition (ICMC-ASR) challenge, which considers the ASR task with multi-speaker overlapping and Mandarin accent dynamics in the ICMC case. We…

In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…

End-to-end transformer-based models epitomize the cutting-edge in Automatic Speech Recognition (ASR) systems. Despite their substantial benefits, these models demand extensive training data to perform optimally, presenting a significant…