paper-with-me

Papers

Optimizing Speech Recognition For The Edge

2019-09-26 · Yuan Shangguan, Jian Li, Qiao Liang, Raziel Alvarez, Ian McGraw

While most deployed speech recognition systems today still run on servers, we are in the midst of a transition towards deployments on edge devices. This leap to the edge is powered by the progression from traditional speech recognition pipelines to end-to-end (E2E) neural architectures, and the parallel development of more efficient neural network topologies and optimization techniques. Thus, we are now able to create highly accurate speech recognizers that are both small and fast enough to execute on typical mobile devices. In this paper, we begin with a baseline RNN-Transducer architecture comprised of Long Short-Term Memory (LSTM) layers. We then experiment with a variety of more computationally efficient layer types, as well as apply optimization techniques like neural connection pruning and parameter quantization to construct a small, high quality, on-device speech recognizer that is an order of magnitude smaller than the baseline system without any optimizations.

📄 PDF Abstract BibTeX arXiv:1909.12408

Code (0)

등록된 구현이 없습니다.

Tasks

Efficient Neural NetworkQuantizationspeech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Triple X: A LLM-Based Multilingual Speech Recognition System for the INTERSPEECH2025 MLC-SLM Challenge

2025-07-23 · Miaomiao Gao, Xiaoxiao Xiang, Yiwen Guo arxiv

This paper describes our Triple X speech recognition system submitted to Task 1 of the Multi-Lingual Conversational Speech Language Modeling (MLC-SLM) Challenge. Our work focuses on optimizing speech recognition accuracy…

Speech Recognition

Enhancing Audiovisual Speech Recognition through Bifocal Preference Optimization

2024-12-26 · Yihan Wu, Yichen Lu, Yifan Peng, Xihua Wang 외

Audiovisual Automatic Speech Recognition (AV-ASR) aims to improve speech recognition accuracy by leveraging visual signals. It is particularly challenging in unconstrained real-world scenarios across various domains due …

Automatic Speech Recognitionspeech-recognitionSpeech Recognition

Reinforcement Learning Based Speech Enhancement for Robust Speech Recognition

2018-11-10

Conventional deep neural network (DNN)-based speech enhancement (SE) approaches aim to minimize the mean square error (MSE) between enhanced speech and clean reference. The MSE-optimized model may not directly improve th…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)reinforcement-learningReinforcement Learning+5

Alignment Knowledge Distillation for Online Streaming Attention-based Speech Recognition

2021-02-28 · Hirofumi Inaguma, Tatsuya Kawahara

This article describes an efficient training method for online streaming attention-based encoder-decoder (AED) automatic speech recognition (ASR) systems. AED models have achieved competitive performance in offline scena…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderKnowledge Distillation+2

Exploiting Beam Search Confidence for Energy-Efficient Speech Recognition

2021-01-22 · Dennis Pinto, Jose-María Arnau, Antonio González

With computers getting more and more powerful and integrated in our daily lives, the focus is increasingly shifting towards more human-friendly interfaces, making Automatic Speech Recognition (ASR) a central player as th…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition