English
Related papers

Related papers: Effective and Efficient One-pass Compression of Sp…

200 papers

Sequential models achieve state-of-the-art results in audio, visual and textual domains with respect to both estimating the data distribution and generating high-quality samples. Efficient sampling for this class of models has however…

Speech recognition on smart devices is challenging owing to the small memory footprint. Hence small size ASR models are desirable. With the use of popular transducer-based models, it has become possible to practically deploy streaming…

Audio and Speech Processing · Electrical Eng. & Systems 2022-01-11 Nauman Dawalatabad , Tushar Vatsal , Ashutosh Gupta , Sungsoo Kim , Shatrughan Singh , Dhananjaya Gowda , Chanwoo Kim

We consider the problem of estimating the sparse time-varying parameter vectors of a point process model in an online fashion, where the observations and inputs respectively consist of binary and continuous time series. We construct a novel…

Neural and Evolutionary Computing · Computer Science 2016-04-20 Alireza Sheikhattar , Jonathan B. Fritz , Shihab A. Shamma , Behtash Babadi

Streaming end-to-end speech recognition models have been widely applied to mobile devices and show significant improvement in efficiency. These models are typically trained on the server using transcribed speech data. However, the server…

Large pretrained language models such as BERT suffer from slow inference and high memory usage, due to their huge size. Recent approaches to compressing BERT rely on iterative pruning and knowledge distillation, which, however, are often…

Computation and Language · Computer Science 2025-02-07 Hyemin Lim , Jaeyeon Lee , Dong-Wan Choi

Wav2vec 2.0 is a state-of-the-art speech recognition model which maps speech audio waveforms into latent representations. The largest version of wav2vec 2.0 contains 317 million parameters. Hence, the inference latency of wav2vec 2.0 will…

Computation and Language · Computer Science 2021-04-02 Zilun Peng , Akshay Budhkar , Ilana Tuil , Jason Levy , Parinaz Sobhani , Raphael Cohen , Jumana Nassour

To mitigate communication overheads in distributed model training, several studies propose the use of compressed stochastic gradients, usually achieved by sparsification or quantization. Such techniques achieve high compression ratios, but…

Machine Learning · Computer Science 2021-03-09 Hongyi Wang , Saurabh Agarwal , Dimitris Papailiopoulos

This paper is focused on the finetuning of acoustic models for speaker adaptation goals on a given gender. We pretrained the Transformer baseline model on Librispeech-960 and conduct experiments with finetuning on the gender-specific test…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-18 Sokolov Artem , Andrey V. Savchenko

Squeeze and Efficient Wav2vec (SEW) is a recently proposed architecture that squeezes the input to the transformer encoder for compute efficient pre-training and inference with wav2vec 2.0 (W2V2) models. In this work, we propose stochastic…

Machine Learning · Computer Science 2022-04-27 Apoorv Vyas , Wei-Ning Hsu , Michael Auli , Alexei Baevski

With the rise and ubiquity of larger deep learning models, the need for high-quality compression techniques is growing in order to deploy these models widely. The sheer parameter count of these models makes it difficult to fit them into the…

Computation and Language · Computer Science 2025-04-01 Neha Verma , Kenton Murray , Kevin Duh

Various Large Language Models~(LLMs) from the Generative Pretrained Transformer(GPT) family have achieved outstanding performances in a wide range of text generation tasks. However, the enormous model sizes have hindered their practical use…

Computation and Language · Computer Science 2024-04-24 Hang Shao , Bei Liu , Bo Xiao , Ke Zeng , Guanglu Wan , Yanmin Qian

Transformer models have achieved remarkable results in various natural language tasks, but they are often prohibitively large, requiring massive memories and computational resources. To reduce the size and complexity of these models, we…

Machine Learning · Computer Science 2023-06-27 Yixiao Li , Yifan Yu , Qingru Zhang , Chen Liang , Pengcheng He , Weizhu Chen , Tuo Zhao

Text-to-speech (TTS) models have achieved remarkable naturalness in recent years, yet like most deep neural models, they have more parameters than necessary. Sparse TTS models can improve on dense models via pruning and extra retraining, or…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-04 Perry Lam , Huayun Zhang , Nancy F. Chen , Berrak Sisman , Dorien Herremans

Large language models have become the cornerstone of natural language processing, but their use comes with substantial costs in terms of compute and memory resources. Sparsification provides a solution to alleviate these resource…

Machine Learning · Computer Science 2024-02-12 Saleh Ashkboos , Maximilian L. Croci , Marcelo Gennari do Nascimento , Torsten Hoefler , James Hensman

This study examines the effectiveness of layer pruning in creating efficient Sentence BERT (SBERT) models. Our goal is to create smaller sentence embedding models that reduce complexity while maintaining strong embedding similarity. We…

Computation and Language · Computer Science 2024-09-24 Anushka Shelke , Riya Savant , Raviraj Joshi

While pruning methods effectively maintain model performance without extra training costs, they often focus solely on preserving crucial connections, overlooking the impact of pruned weights on subsequent fine-tuning or distillation,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Hyeonjin Kim , Jaejun Yoo

Benefiting from massive and diverse data sources, speech foundation models exhibit strong generalization and knowledge transfer capabilities to a wide range of downstream tasks. However, a limitation arises from their exclusive handling of…

Audio and Speech Processing · Electrical Eng. & Systems 2024-12-10 Pengcheng Guo , Xuankai Chang , Hang Lv , Shinji Watanabe , Lei Xie

Deep learning has become a de facto method of choice for speech enhancement tasks with significant improvements in speech quality. However, real-time processing with reduced size and computations for low-power edge devices drastically…

Audio and Speech Processing · Electrical Eng. & Systems 2024-05-28 Monisankha Pal , Arvind Ramanathan , Ted Wada , Ashutosh Pandey

Large language models (LLMs) excel in language tasks, especially with supervised fine-tuning after pre-training. However, their substantial memory and computational requirements hinder practical applications. Structural pruning, which…

Machine Learning · Computer Science 2025-01-28 Yijiang Liu , Huanrui Yang , Youxin Chen , Rongyu Zhang , Miao Wang , Yuan Du , Li Du

As deep neural networks are increasingly used in applications suited for low-power devices, a fundamental dilemma becomes apparent: the trend is to grow models to absorb increasing data that gives rise to memory intensive; however low-power…

Computer Vision and Pattern Recognition · Computer Science 2023-02-21 Weiyu Guo , Jiabin Ma , Liang Wang , Yongzhen Huang