Related papers: 4-bit Conformer with Native Quantization Aware Tra…

This paper presents a novel mixed-precision quantization approach for speech foundation models that tightly integrates mixed-precision learning and quantized model parameter estimation into one single model compression stage. Experiments…

Recent advances in speech recognition and translation rely on hundreds of thousands of hours of Internet speech data. We argue that state-of-the art accuracy can be reached without relying on web-scale data. Canary - multilingual ASR and…

Automatic speech recognition research focuses on training and evaluating on static datasets. Yet, as speech models are increasingly deployed on personal devices, such models encounter user-specific distributional shifts. To simulate this…

The Conformer model is an excellent architecture for speech recognition modeling that effectively utilizes the hybrid losses of connectionist temporal classification (CTC) and attention to train model parameters. To improve the decoding…

The recently proposed conformer architecture has been successfully used for end-to-end automatic speech recognition (ASR) architectures achieving state-of-the-art performance on different datasets. To our best knowledge, the impact of using…

Automatic speech recognition (ASR) is crucial for human-machine interaction in diverse applications like conversational agents, industrial robotics, call center automation, and automated subtitling. However, developing high-performance ASR…

Self-supervised learning (SSL)-based speech models are extensively used for full-stack speech processing. However, it has been observed that improving SSL-based speech representations using unlabeled speech for content-related tasks is…

This paper presents a method for selecting appropriate synthetic speech samples from a given large text-to-speech (TTS) dataset as supplementary training data for an automatic speech recognition (ASR) model. We trained a neural network,…

Quantization stands as a pivotal technique for large language model (LLM) serving, yet it poses significant challenges particularly in achieving effective low-bit quantization. The limited numerical mapping makes the quantized model produce…

Self-supervised learning (SSL) is a powerful tool that allows learning of underlying representations from unlabeled data. Transformer based models such as wav2vec 2.0 and HuBERT are leading the field in the speech domain. Generally these…

Conformer has achieved impressive results in Automatic Speech Recognition (ASR) by leveraging transformer's capturing of content-based global interactions and convolutional neural network's exploiting of local features. In Conformer, two…

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…

Large Language Models (LLMs) are proficient in natural language processing tasks, but their deployment is often restricted by extensive parameter sizes and computational demands. This paper focuses on post-training quantization (PTQ) in…

Advancements in monaural speech enhancement (SE) techniques have greatly improved the perceptual quality of speech. However, integrating these techniques into automatic speech recognition (ASR) systems has not yielded the expected…

Personalizing Automatic Speech Recognition (ASR) for non-normative speech remains challenging because data collection is labor-intensive and model training is technically complex. To address these limitations, we propose Adapt4Me, a…

In this paper, we show that a simple self-supervised pre-trained audio model can achieve comparable inference efficiency to more complicated pre-trained models with speech transformer encoders. These speech transformers rely on mixing…

With the widespread application of automatic speech recognition (ASR) systems, their vulnerability to adversarial attacks has been extensively studied. However, most existing adversarial examples are generated on specific individual models,…

We present a frontend for improving robustness of automatic speech recognition (ASR), that jointly implements three modules within a single model: acoustic echo cancellation, speech enhancement, and speech separation. This is achieved by…

End-to-end models are favored in automatic speech recognition (ASR) because of their simplified system structure and superior performance. Among these models, Transformer and Conformer have achieved state-of-the-art recognition accuracy in…

End-to-end training of automated speech recognition (ASR) systems requires massive data and compute resources. We explore transfer learning based on model adaptation as an approach for training ASR models under constrained GPU memory,…