Related papers: Integer-only Zero-shot Quantization for Efficient …

Quantization is essential for deploying large audio language models (LALMs) efficiently in resource-constrained environments. However, its impact on complex tasks, such as zero-shot audio spoofing detection, remains underexplored. This…

Word error rate (WER) is a standard metric for the evaluation of Automated Speech Recognition (ASR) systems. However, WER fails to provide a fair evaluation of human perceived quality in presence of spelling variations, abbreviations, or…

Zero-shot quantization is a promising approach for developing lightweight deep neural networks when data is inaccessible owing to various reasons, including cost and issues related to privacy. By exploiting the learned parameters ($\mu$ and…

Recent advances in speech foundation models are largely driven by scaling both model size and data, enabling them to perform a wide range of tasks, including speech recognition. Traditionally, ASR models are evaluated using metrics like…

Quantization is essential for reducing the computational cost and memory usage of deep neural networks, enabling efficient inference on low-precision hardware. Despite the growing adoption of uniform and floating-point quantization schemes,…

Deep learning as a means to inferencing has proliferated thanks to its versatility and ability to approach or exceed human-level accuracy. These computational models have seemingly insatiable appetites for computational resources not only…

Integer quantization of neural networks can be defined as the approximation of the high precision computation of the canonical neural network formulation, using reduced integer precision. It plays a significant role in the efficient…

Efficient single-image super-resolution (SISR) requires balancing reconstruction fidelity, model compactness, and robustness under low-bit deployment, which is especially challenging for x3 SR. We present a deployment-oriented quantized…

Quantizing the floating-point weights and activations of deep convolutional neural networks to fixed-point representation yields reduced memory footprints and inference time. Recently, efforts have been afoot towards zero-shot quantization…

Modern speech synthesis systems have improved significantly, with synthetic speech being indistinguishable from real speech. However, efficient and holistic evaluation of synthetic speech still remains a significant challenge. Human…

Recent machine learning methods use increasingly large deep neural networks to achieve state of the art results in various tasks. The gains in performance come at the cost of a substantial increase in computation and storage requirements.…

State-of-the-art hybrid automatic speech recognition (ASR) system exploits deep neural network (DNN) based acoustic models (AM) trained with Lattice Free-Maximum Mutual Information (LF-MMI) criterion and n-gram language models. The AMs…

We propose a novel one-pass multiple ASR systems joint compression and quantization approach using an all-in-one neural model. A single compression cycle allows multiple nested systems with varying Encoder depths, widths, and quantization…

Quantization for deep neural networks have afforded models for edge devices that use less on-board memory and enable efficient low-power inference. In this paper, we present a comparison of model-parameter driven quantization approaches…

Automatic Pronunciation Assessment (APA) is vital for computer-assisted language learning. Prior methods rely on annotated speech-text data to train Automatic Speech Recognition (ASR) models or speech-score data to train regression models.…

Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition (ASR). When using appropriate modeling units, e.g., byte-pair encoded characters, these systems are in principal open vocabulary…

Network quantization has proven to be a powerful approach to reduce the memory and computational demands of deep learning models for deployment on resource-constrained devices. However, traditional quantization methods often rely on access…

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…

This work investigates two strategies for zero-shot non-intrusive speech assessment leveraging large language models. First, we explore the audio analysis capabilities of GPT-4o. Second, we propose GPT-Whisper, which uses Whisper as an…

While neural networks have advanced the frontiers in many machine learning applications, they often come at a high computational cost. Reducing the power and latency of neural network inference is vital to integrating modern networks into…