Related papers: A Model for Every User and Budget: Label-Free and …

Quantization-aware training (QAT) is a representative model compression method to reduce redundancy in weights and activations. However, most existing QAT methods require end-to-end training on the entire dataset, which suffers from long…

Fine-tuning large language models (LLMs) under resource constraints is a significant challenge in deep learning. Low-Rank Adaptation (LoRA), pruning, and quantization are all effective methods for improving resource efficiency. However,…

Large language models (LLMs) have significantly advanced the natural language processing paradigm but impose substantial demands on memory and computational resources. Quantization is one of the most effective ways to reduce memory…

Attention mechanisms have revolutionized natural language processing. Combining them with quantum computing aims to further advance this technology. This paper introduces a novel Quantum Mixed-State Self-Attention Network (QMSAN) for…

This study investigates the performance of personalized automatic speech recognition (ASR) for recognizing disordered speech using small amounts of per-speaker adaptation data. We trained personalized models for 195 individuals with…

Deep learning has made remarkable progress recently, largely due to the availability of large, well-labeled datasets. However, the training on such datasets elevates costs and computational demands. To address this, various techniques like…

We propose a novel end-to-end multi-talker automatic speech recognition (ASR) framework that enables both multi-speaker (MS) ASR and target-speaker (TS) ASR. Our proposed model is trained in a fully end-to-end manner, incorporating speaker…

Quantization is a popular technique that $transforms$ the parameter representation of a neural network from floating-point numbers into lower-precision ones ($e.g.$, 8-bit integers). It reduces the memory footprint and the computational…

We introduce the largest transcribed Arabic speech corpus, QASR, collected from the broadcast domain. This multi-dialect speech dataset contains 2,000 hours of speech sampled at 16kHz crawled from Aljazeera news channel. The dataset is…

In hybrid automatic speech recognition (ASR) systems, the vocabulary size is unambiguous, typically determined by the number of phones, bi-phones, or tri-phones present in the language. In contrast, end-to-end ASR systems derive their…

Recognition of overlapped speech has been a highly challenging task to date. State-of-the-art multi-channel speech separation system are becoming increasingly complex and expensive for practical applications. To this end, low-bit neural…

The widespread adoption of voice-enabled authentication and audio biometric systems have significantly increased privacy vulnerabilities associated with sensitive speech data. Compliance with privacy regulations such as GDPR's right to be…

In the design of customer relationship management (CRM) systems, accurately identifying customer types and offering personalized services are key to enhancing customer satisfaction and loyalty. However, this process faces the challenge of…

How can we accurately quantize a pre-trained model without any data? Quantization algorithms are widely used for deploying neural networks on resource-constrained edge devices. Zero-shot Quantization (ZSQ) addresses the crucial and…

We propose a self-refining framework that enhances ASR performance with only unlabeled datasets. The process starts with an existing ASR model generating pseudo-labels on unannotated speech, which are then used to train a high-fidelity…

Large language models (LLMs) excel at natural language tasks but face deployment challenges due to their growing size outpacing GPU memory advancements. Model quantization mitigates this issue by lowering weight and activation precision,…

As machine learning inferences increasingly move to edge devices, adapting to diverse computational capabilities, hardware, and memory constraints becomes more critical. Instead of relying on a pre-trained model fixed for all future…

On-device automatic speech recognition systems face several challenges compared to server-based systems. They have to meet stricter constraints in terms of speed, disk size and memory while maintaining the same accuracy. Often they have to…

Large speech models are rapidly gaining traction in research community. As a result, model compression has become an important topic, so that these models can fit in memory and be served with reduced cost. Practical approaches for…

Neural network quantization has become an important research area due to its great impact on deployment of large models on resource constrained devices. In order to train networks that can be effectively discretized without loss of…