相关论文: Advances in All-Neural Speech Recognition

In this work, we investigate two popular end-to-end automatic speech recognition (ASR) models, namely Connectionist Temporal Classification (CTC) and RNN-Transducer (RNN-T), for offline recognition of voice search queries, with up to 2B…

This paper presents an analysis of three end-to-end models developed for the NOCASA 2025 Challenge, aimed at automatic word-level pronunciation assessment for children learning Norwegian as a second language. Our models include an…

For end-to-end speech translation, regularizing the encoder with the Connectionist Temporal Classification (CTC) objective using the source transcript or target translation as labels can greatly improve quality metrics. However, CTC demands…

Training automatic speech recognition (ASR) systems requires large amounts of data in the target language in order to achieve good performance. Whereas large training corpora are readily available for languages like English, there exists a…

Achieving high accuracy with end-to-end speech recognizers requires careful parameter initialization prior to training. Otherwise, the networks may fail to find a good local optimum. This is particularly true for online networks, such as…

While end-to-end ASR systems have proven competitive with the conventional hybrid approach, they are prone to accuracy degradation when it comes to noisy and low-resource conditions. In this paper, we argue that, even in such difficult…

Speech tokenization is the task of representing speech signals as a sequence of discrete units. Such representations can be later used for various downstream tasks including automatic speech recognition, text-to-speech, etc. More relevant…

Deploying end-to-end speech recognition models with limited computing resources remains challenging, despite their impressive performance. Given the gradual increase in model size and the wide range of model applications, selectively…

Modern speaker verification systems primarily rely on speaker embeddings, followed by verification based on cosine similarity between the embedding vectors of the enrollment and test utterances. While effective, these methods struggle with…

Code-switching speech recognition has attracted an increasing interest recently, but the need for expert linguistic knowledge has always been a big issue. End-to-end automatic speech recognition (ASR) simplifies the building of ASR systems…

Confidence measure is a performance index of particular importance for automatic speech recognition (ASR) systems deployed in real-world scenarios. In the present study, utterance-level neural confidence measure (NCM) in end-to-end…

This study reports our efforts to improve automatic recognition of suprasegmentals by fine-tuning wav2vec 2.0 with CTC, a method that has been successful in automatic speech recognition. We demonstrate that the method can improve the…

Recent advances in unsupervised speech representation learning discover new approaches and provide new state-of-the-art for diverse types of speech processing tasks. This paper presents an investigation of using wav2vec 2.0 deep speech…

This paper reports our work on building up a Cantonese Speech-to-Text (STT) system with a syllable based acoustic model. This is a part of an effort in building a STT system to aid dyslexic students who have cognitive deficiency in writing…

End-to-end models for robust automatic speech recognition (ASR) have not been sufficiently well-explored in prior work. With end-to-end models, one could choose to preprocess the input speech using speech enhancement techniques and train…

End-to-end (E2E) systems have shown comparable performance to hybrid systems for automatic speech recognition (ASR). Word timings, as a by-product of ASR, are essential in many applications, especially for subtitling and computer-aided…

We present a simple and efficient auxiliary loss function for automatic speech recognition (ASR) based on the connectionist temporal classification (CTC) objective. The proposed objective, an intermediate CTC loss, is attached to an…

Attention-based methods and Connectionist Temporal Classification (CTC) network have been promising research directions for end-to-end Automatic Speech Recognition (ASR). The joint CTC/Attention model has achieved great success by utilizing…

Unsupervised speech recognition has shown great potential to make Automatic Speech Recognition (ASR) systems accessible to every language. However, existing methods still heavily rely on hand-crafted pre-processing. Similar to the trend of…

Different studies have shown the importance of visual cues throughout the speech perception process. In fact, the development of audiovisual approaches has led to advances in the field of speech technologies. However, although noticeable…