Image de couverture de livre

Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Yang, Shangguan, Yuan, Wang, Yuhao, Lai, Liangzhen, Chang, Ernie, Zhao, Changsheng, Shi, Yangyang, Chandra, Vikas
Format:	Preprint
Publié:	2024
Sujets:	Sound Machine Learning Audio and Speech Processing
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Folding Attention: Memory and Power Optimization for On-Device Transformer-based Streaming Speech Recognition
par: Li, Yang, et autres
Publié: (2023)

High Fidelity Text-Guided Music Editing via Single-Stage Flow Matching
par: Lan, Gael Le, et autres
Publié: (2024)

CUSIDE-T: Chunking, Simulating Future and Decoding for Transducer based Streaming ASR
par: Zhao, Wenbo, et autres
Publié: (2024)

Streaming Bilingual End-to-End ASR model using Attention over Multiple Softmax
par: Patil, Aditya, et autres
Publié: (2024)

Multichannel Long-Term Streaming Neural Speech Enhancement for Static and Moving Speakers
par: Quan, Changsheng, et autres
Publié: (2024)

Scaling Multi-Talker ASR with Speaker-Agnostic Activity Streams
par: He, Xiluo, et autres
Publié: (2025)

Lightweight Target-Speaker-Based Overlap Transcription for Practical Streaming ASR
par: Pražák, Aleš, et autres
Publié: (2025)

Mobile Recording Device Recognition Based Cross-Scale and Multi-Level Representation Learning
par: Zeng, Chunyan, et autres
Publié: (2024)

Delayed-KD: Delayed Knowledge Distillation based CTC for Low-Latency Streaming ASR
par: Li, Longhao, et autres
Publié: (2025)

Breaking the Barriers of Text-Hungry and Audio-Deficient AI
par: Tembine, Hamidou, et autres
Publié: (2025)

Breaking Resource Barriers in Speech Emotion Recognition via Data Distillation
par: Chang, Yi, et autres
Publié: (2024)

DITTO: Data-efficient and Fair Targeted Subset Selection for ASR Accent Adaptation
par: Kothawade, Suraj, et autres
Publié: (2021)

Semi-Autoregressive Streaming ASR With Label Context
par: Arora, Siddhant, et autres
Publié: (2023)

Mamba for Streaming ASR Combined with Unimodal Aggregation
par: Fang, Ying, et autres
Publié: (2024)

Unifying Streaming and Non-streaming Zipformer-based ASR
par: Sharma, Bidisha, et autres
Publié: (2025)

Speaker Adaptation for Quantised End-to-End ASR Models
par: Zhao, Qiuming, et autres
Publié: (2024)

SQ-Whisper: Speaker-Querying based Whisper Model for Target-Speaker ASR
par: Guo, Pengcheng, et autres
Publié: (2024)

Target Speaker ASR with Whisper
par: Polok, Alexander, et autres
Publié: (2024)

Index-ASR Technical Report
par: Song, Zheshu, et autres
Publié: (2025)

The USTC-NERCSLIP Systems for The ICMC-ASR Challenge
par: Wu, Minghui, et autres
Publié: (2024)

SLAP: Scalable Language-Audio Pretraining with Variable-Duration Audio and Multi-Objective Training
par: Mei, Xinhao, et autres
Publié: (2026)

SyncFlow: Toward Temporally Aligned Joint Audio-Video Generation from Text
par: Liu, Haohe, et autres
Publié: (2024)

Towards Robust Dysarthric Speech Recognition: LLM-Agent Post-ASR Correction Beyond WER
par: Zheng, Xiuwen, et autres
Publié: (2026)

Speech Emotion Recognition with ASR Integration
par: Li, Yuanchao
Publié: (2026)

Efficient Scaling for LLM-based ASR
par: Mu, Bingshen, et autres
Publié: (2025)

Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whisper
par: Thorbecke, Iuliia, et autres
Publié: (2024)

SAML: Speaker Adaptive Mixture of LoRA Experts for End-to-End ASR
par: Zhao, Qiuming, et autres
Publié: (2024)

kNN-CTC: Enhancing ASR via Retrieval of CTC Pseudo Labels
par: Zhou, Jiaming, et autres
Publié: (2023)

EFFUSE: Efficient Self-Supervised Feature Fusion for E2E ASR in Low Resource and Multilingual Scenarios
par: Srivastava, Tejes, et autres
Publié: (2023)

Romanization Encoding For Multilingual ASR
par: Ding, Wen, et autres
Publié: (2024)

BEAST: Online Joint Beat and Downbeat Tracking Based on Streaming Transformer
par: Chang, Chih-Cheng, et autres
Publié: (2023)

dLLM-ASR: A Faster Diffusion LLM-based Framework for Speech Recognition
par: Tian, Wenjie, et autres
Publié: (2026)

LUPET: Incorporating Hierarchical Information Path into Multilingual ASR
par: Liu, Wei, et autres
Publié: (2024)

persoDA: Personalized Data Augmentation for Personalized ASR
par: Parada, Pablo Peso, et autres
Publié: (2025)

Comparative Analysis of ASR Methods for Speech Deepfake Detection
par: Salvi, Davide, et autres
Publié: (2024)

Consistency Based Unsupervised Self-training For ASR Personalisation
par: Zhang, Jisi, et autres
Publié: (2024)

Crossmodal ASR Error Correction with Discrete Speech Units
par: Li, Yuanchao, et autres
Publié: (2024)

Joint ASR and Speaker Role Tagging with Serialized Output Training
par: Xu, Anfeng, et autres
Publié: (2025)

Learning When to Trust Which Teacher for Weakly Supervised ASR
par: Agrawal, Aakriti, et autres
Publié: (2023)

Technical Report: A Practical Guide to Kaldi ASR Optimization
par: Hong, Mengze, et autres
Publié: (2025)