Related papers: Improving CTC-based speech recognition via knowled…

Recently, self-supervised pretraining has achieved impressive results in end-to-end (E2E) automatic speech recognition (ASR). However, the dominant sequence-to-sequence (S2S) E2E model is still hard to fully utilize the self-supervised…

For real-world deployment of automatic speech recognition (ASR), the system is desired to be capable of fast inference while relieving the requirement of computational resources. The recently proposed end-to-end ASR system based on…

The pre-training models such as BERT have achieved great results in various natural language processing problems. However, a large number of parameters need significant amounts of memory and the consumption of inference time, which makes it…

Previous work has shown that neural encoder-decoder speech recognition can be improved with hierarchical multitask learning, where auxiliary tasks are added at intermediate layers of a deep encoder. We explore the effect of hierarchical…

Voice conversion refers to transferring speaker identity with well-preserved content. Better disentanglement of speech representations leads to better voice conversion. Recent studies have found that phonetic information from input audio…

We study the possibilities of building a non-autoregressive speech-to-text translation model using connectionist temporal classification (CTC), and use CTC-based automatic speech recognition as an auxiliary task to improve the performance.…

Previous works on emotion recognition in conversation (ERC) follow a two-step paradigm, which can be summarized as first producing context-independent features via fine-tuning pretrained language models (PLMs) and then analyzing contextual…

Techniques for multi-lingual and cross-lingual speech recognition can help in low resource scenarios, to bootstrap systems and enable analysis of new languages and domains. End-to-end approaches, in particular sequence-based techniques, are…

Large-scale pre-trained language model such as BERT has achieved great success in language understanding tasks. However, it remains an open question how to utilize BERT for language generation. In this paper, we present a novel approach,…

In this work, we present a simple but effective method, CTCBERT, for advancing hidden-unit BERT (HuBERT). HuBERT applies a frame-level cross-entropy (CE) loss, which is similar to most acoustic model training. However, CTCBERT performs the…

Multilingual models for Automatic Speech Recognition (ASR) are attractive as they have been shown to benefit from more training data, and better lend themselves to adaptation to under-resourced languages. However, initialisation from…

Semi-supervised learning (SSL) is an active area of research which aims to utilize unlabelled data in order to improve the accuracy of speech recognition systems. The current study proposes a methodology for integration of two key ideas: 1)…

Models for streaming speech translation (ST) can achieve high accuracy and low latency if they're developed with vast amounts of paired audio in the source language and written text in the target language. Yet, these text labels for the…

Connectionist temporal classification (CTC) is a popular sequence prediction approach for automatic speech recognition that is typically used with models based on recurrent neural networks (RNNs). We explore whether deep convolutional…

The CTC-based automatic speech recognition (ASR) models without the external language model usually lack the capacity to model conditional dependencies and textual interactions. In this paper, we present a Gated Interlayer Collaboration…

Self-supervised Transformer based models, such as wav2vec 2.0 and HuBERT, have produced significant improvements over existing approaches to automatic speech recognition (ASR). This is evident in the performance of the wav2vec 2.0 based…

End-to-end speech recognition systems usually require huge amounts of labeling resource, while annotating the speech data is complicated and expensive. Active learning is the solution by selecting the most valuable samples for annotation.…

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…

Active learning has been shown to be an effective way to alleviate some of the effort required in utilising large collections of unlabelled data for machine learning tasks without needing to fully label them. The representation mechanism…

End-to-end multilingual speech recognition models handle multiple languages through a single model, often incorporating language identification to automatically detect the language of incoming speech. Since the common scenario is where the…