Related papers: USM-Lite: Quantization and Sparsity Aware Fine-tun…

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…

Model compression has become an emerging need as the sizes of modern speech systems rapidly increase. In this paper, we study model weight quantization, which directly reduces the memory footprint to accommodate computationally…

Reducing the latency and model size has always been a significant research problem for live Automatic Speech Recognition (ASR) application scenarios. Along this direction, model quantization has become an increasingly popular approach to…

Recent end-to-end automatic speech recognition (ASR) models have become increasingly larger, making them particularly challenging to be deployed on resource-constrained devices. Model quantisation is an effective solution that sometimes…

We introduce the Universal Speech Model (USM), a single large model that performs automatic speech recognition (ASR) across 100+ languages. This is achieved by pre-training the encoder of the model on a large unlabeled multilingual dataset…

End-to-end models have shown superior performance for automatic speech recognition (ASR). However, such models are often very large in size and thus challenging to deploy on resource-constrained edge devices. While quantisation can reduce…

While significant improvements have been made in recent years in terms of end-to-end automatic speech recognition (ASR) performance, such improvements were obtained through the use of very large neural networks, unfit for embedded use on…

With the development of hardware for machine learning, newer models often come at the cost of both increased sizes and computational complexity. In effort to improve the efficiency for these models, we apply and investigate recent…

Automatic Speech Recognition (ASR) has seen remarkable advancements with deep neural networks, such as Transformer and Conformer. However, these models typically have large model sizes and high inference costs, posing a challenge to deploy…

In order to achieve high accuracy for machine learning (ML) applications, it is essential to employ models with a large number of parameters. Certain applications, such as Automatic Speech Recognition (ASR), however, require real-time…

We investigate the impact of aggressive low-precision representations of weights and activations in two families of large LSTM-based architectures for Automatic Speech Recognition (ASR): hybrid Deep Bidirectional LSTM - Hidden Markov Models…

Masked speech modeling (MSM) methods such as wav2vec2 or w2v-BERT learn representations over speech frames which are randomly masked within an utterance. While these methods improve performance of Automatic Speech Recognition (ASR) systems,…

Personalization of automatic speech recognition (ASR) models is a widely studied topic because of its many practical applications. Most recently, attention-based contextual biasing techniques are used to improve the recognition of rare…

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…

End-to-end automatic speech recognition (ASR) models are increasingly large and complex to achieve the best possible accuracy. In this paper, we build an AutoML system that uses reinforcement learning (RL) to optimize the per-layer…

Recent advances in Automatic Speech Recognition (ASR) have demonstrated remarkable accuracy and robustness in diverse audio applications, such as live transcription and voice command processing. However, deploying these models on…

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.,…

Transformer models have been used in automatic speech recognition (ASR) successfully and yields state-of-the-art results. However, its performance is still affected by speaker mismatch between training and test data. Further finetuning a…

Large-scale universal speech models (USM) are already used in production. However, as the model size grows, the serving cost grows too. Serving cost of large models is dominated by model size that is why model size reduction is an important…

As large language models (LLMs) grow in size, efficient compression techniques like quantization and sparsification are critical. While quantization maintains performance with reduced precision, structured sparsity methods, such as N:M…