Related papers: Reducing the gap between streaming and non-streami…
Knowledge distillation, transferring knowledge from a teacher model to a student model, has emerged as a powerful technique in neural machine translation for compressing models or simplifying training targets. Knowledge distillation…
End-to-end speech recognition is a promising technology for enabling compact automatic speech recognition (ASR) systems since it can unify the acoustic and language model into a single neural network. However, as a drawback, training of…
Despite that current reading comprehension systems have achieved significant advancements, their promising performances are often obtained at the cost of making an ensemble of numerous models. Besides, existing approaches are also…
The unified streaming and non-streaming speech recognition model has achieved great success due to its comprehensive capabilities. In this paper, we propose to improve the accuracy of the unified model by bridging the inherent…
In this paper, we present an in-depth study on online attention mechanisms and distillation techniques for dual-mode (i.e., joint online and offline) ASR using the Conformer Transducer. In the dual-mode Conformer Transducer model, layers…
Automatic speech recognition (ASR) and speech translation (ST) can both use neural transducers as the model structure. It is thus possible to use a single transducer model to perform both tasks. In real-world applications, such joint ASR…
Streaming end-to-end automatic speech recognition (ASR) systems are widely used in everyday applications that require transcribing speech to text in real-time. Their minimal latency makes them suitable for such tasks. Unlike their…
State-of-the-art frameworks in self-supervised learning have recently shown that fully utilizing transformer-based models can lead to performance boost compared to conventional CNN models. Striving to maximize the mutual information of two…
Speech emotion recognition (SER) is the task of recognising human's emotional states from speech. SER is extremely prevalent in helping dialogue systems to truly understand our emotions and become a trustworthy human conversational partner.…
This paper addresses the problem of model compression via knowledge distillation. To this end, we propose a new knowledge distillation method based on transferring feature statistics, specifically the channel-wise mean and variance, from…
Knowledge distillation provides an effective way to transfer knowledge via teacher-student learning, where most existing distillation approaches apply a fixed pre-trained model as teacher to supervise the learning of student network. This…
Automatic Speech Recognition (ASR) systems are known to exhibit difficulties when transcribing children's speech. This can mainly be attributed to the absence of large children's speech corpora to train robust ASR models and the resulting…
While large language models (LLMs) have been applied to automatic speech recognition (ASR), the task of making the model streamable remains a challenge. This paper proposes a novel model architecture, Transducer-Llama, that integrates LLMs…
Recent advancement in deep learning encouraged developing large automatic speech recognition (ASR) models that achieve promising results while ignoring computational and memory constraints. However, deploying such models on low resource…
Semi-supervised regression (SSR), which aims to predict continuous scores for samples while reducing the reliance on large-scale labeled data, has recently attracted considerable attention across various applications, including computer…
We present a novel large-context end-to-end automatic speech recognition (E2E-ASR) model and its effective training method based on knowledge distillation. Common E2E-ASR models have mainly focused on utterance-level processing in which…
Diffusion language models intrinsically fail to capture correlations between decoded tokens, which leads to a harsh trade-off between sampling quality and throughput. To solve this issue, we propose DiLaDiff, a variant of masked diffusion…
Implicit discourse relation recognition (IDRR) aims at recognizing the discourse relation between two text segments without an explicit connective. Recently, the prompt learning has just been applied to the IDRR task with great performance…
Transfer learning (TL) is widely used in conventional hybrid automatic speech recognition (ASR) system, to transfer the knowledge from source to target language. TL can be applied to end-to-end (E2E) ASR system such as recurrent neural…
Many Automatic Speech Recognition (ASR) applications require streaming processing of the audio data. In streaming mode, ASR systems need to start transcribing the input stream before it is complete, i.e., the systems have to process a…