Related papers: 2-bit Conformer quantization for automatic speech …

Speaker adaptation is important to build robust automatic speech recognition (ASR) systems. In this work, we investigate various methods for speaker adaptive training (SAT) based on feature-space approaches for a conformer-based acoustic…

The impressive capability and versatility of large language models (LLMs) have aroused increasing attention in automatic speech recognition (ASR), with several pioneering studies attempting to build integrated ASR models by connecting a…

Evaluating automatic speech recognition (ASR) systems is a classical but difficult and still open problem, which often boils down to focusing only on the word error rate (WER). However, this metric suffers from many limitations and does not…

A key challenge for automatic speech recognition (ASR) systems is to model the speaker level variability. In this paper, compact speaker dependent learning hidden unit contributions (LHUC) are used to facilitate both speaker adaptive…

Recent advances in speech-aware language models have coupled strong acoustic encoders with large language models, enabling systems that move beyond transcription to produce richer outputs. Among these, word-level timestamp prediction is…

The benefits of most large language models come with steep and often hidden economic and environmental costs due to their resource usage inefficiency during deployment. Model quantization improves energy and memory efficiency through…

Modern speech enhancement algorithms achieve remarkable noise suppression by means of large recurrent neural networks (RNNs). However, large RNNs limit practical deployment in hearing aid hardware (HW) form-factors, which are battery…

In this paper we present a simple and computationally efficient quantization scheme that enables us to reduce the resolution of the parameters of a neural network from 32-bit floating point values to 8-bit integer values. The proposed…

Multilingual speech data often suffer from long-tailed language distribution, resulting in performance degradation. However, multilingual text data is much easier to obtain, yielding a more useful general language model. Hence, we are…

Automatic speech recognition (ASR) systems degrade significantly under noisy conditions. Recently, speech enhancement (SE) is introduced as front-end to reduce noise for ASR, but it also suppresses some important speech information, i.e.,…

End-to-end (E2E) automatic speech recognition (ASR) systems lack the distinct language model (LM) component that characterizes traditional speech systems. While this simplifies the model architecture, it complicates the task of…

Large-scale language models (LLMs) such as GPT-2, BERT and RoBERTa have been successfully applied to ASR N-best rescoring. However, whether or how they can benefit competitive, near state-of-the-art ASR systems remains unexplored. In this…

As large language models (LLMs) continue to grow in size and complexity, efficient checkpoint saving\&loading has become crucial for managing storage, memory usage, and fault tolerance in LLM training. The current works do not…

In recent years, neural models trained on large multilingual text and speech datasets have shown great potential for supporting low-resource languages. This study investigates the performances of two state-of-the-art Automatic Speech…

On-device end-to-end speech recognition poses a high requirement on model efficiency. Most prior works improve the efficiency by reducing model sizes. We propose to reduce the complexity of model architectures in addition to model sizes.…

While speech large language models (SpeechLLMs) have advanced standard automatic speech recognition (ASR), contextual biasing for named entities and rare words remains challenging, especially at scale. To address this, we propose BR-ASR: a…

Automatic speech recognition (ASR) has the potential to substantially reduce manual annotation effort in child speech research by generating automatic transcriptions. However, obtaining reliably high-quality ASR transcriptions for child…

Self-supervised speech recognition models require considerable labeled training data for learning high-fidelity representations for Automatic Speech Recognition (ASR) which is computationally demanding and time-consuming. We consider the…

Creating Automatic Speech Recognition (ASR) systems that are robust and resilient to classroom conditions is paramount to the development of AI tools to aid teachers and students. In this work, we study the efficacy of continued pretraining…

Recent success in speech representation learning enables a new way to leverage unlabeled data to train speech recognition model. In speech representation learning, a large amount of unlabeled data is used in a self-supervised manner to…