Copertina

Whisper in Medusa's Ear: Multi-head Efficient Decoding for Transformer-based ASR

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Segal-Feldman, Yael, Shamsian, Aviv, Navon, Aviv, Hetz, Gill, Keshet, Joseph
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Audio and Speech Processing Artificial Intelligence Machine Learning Sound
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

FlowTSE: Target Speaker Extraction with Flow Matching
di: Navon, Aviv, et al.
Pubblicazione: (2025)

Drax: Speech Recognition with Discrete Flow Matching
di: Navon, Aviv, et al.
Pubblicazione: (2025)

Keyword-Guided Adaptation of Automatic Speech Recognition
di: Shamsian, Aviv, et al.
Pubblicazione: (2024)

Beyond Transcription: Mechanistic Interpretability in ASR
di: Glazer, Neta, et al.
Pubblicazione: (2025)

UmbraTTS: Adapting Text-to-Speech to Environmental Contexts with Flow Matching
di: Glazer, Neta, et al.
Pubblicazione: (2025)

Keyword Spotting with Hyper-Matched Filters for Small Footprint Devices
di: Segal-Feldman, Yael, et al.
Pubblicazione: (2025)

LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading
di: Yemini, Yochai, et al.
Pubblicazione: (2023)

SQ-Whisper: Speaker-Querying based Whisper Model for Target-Speaker ASR
di: Guo, Pengcheng, et al.
Pubblicazione: (2024)

BrainWhisperer: Leveraging Large-Scale ASR Models for Neural Speech Decoding
di: Boccato, Tommaso, et al.
Pubblicazione: (2026)

Target Speaker ASR with Whisper
di: Polok, Alexander, et al.
Pubblicazione: (2024)

Investigation of Whisper ASR Hallucinations Induced by Non-Speech Audio
di: Barański, Mateusz, et al.
Pubblicazione: (2025)

WhisperRT -- Turning Whisper into a Causal Streaming Model
di: Krichli, Tomer, et al.
Pubblicazione: (2025)

Whisper-CD: Accurate Long-Form Speech Recognition using Multi-Negative Contrastive Decoding
di: Ahn, Hoseong, et al.
Pubblicazione: (2026)

WhisperKit: On-device Real-time ASR with Billion-Scale Transformers
di: Orhon, Atila, et al.
Pubblicazione: (2025)

Efficient Scaling for LLM-based ASR
di: Mu, Bingshen, et al.
Pubblicazione: (2025)

CUSIDE-T: Chunking, Simulating Future and Decoding for Transducer based Streaming ASR
di: Zhao, Wenbo, et al.
Pubblicazione: (2024)

A Comparative Study of LLM-based ASR and Whisper in Low Resource and Code Switching Scenario
di: Song, Zheshu, et al.
Pubblicazione: (2024)

State-Space Models in Efficient Whispered and Multi-dialect Speech Recognition
di: Farhadipour, Aref, et al.
Pubblicazione: (2025)

M2R-Whisper: Multi-stage and Multi-scale Retrieval Augmentation for Enhancing Whisper
di: Zhou, Jiaming, et al.
Pubblicazione: (2024)

Whisfusion: Parallel ASR Decoding via a Diffusion Transformer
di: Kwon, Taeyoun, et al.
Pubblicazione: (2025)

Adapting Whisper for Streaming Speech Recognition via Two-Pass Decoding
di: Zhou, Haoran, et al.
Pubblicazione: (2025)

WhispEar: A Bi-directional Framework for Scaling Whispered Speech Conversion via Pseudo-Parallel Whisper Generation
di: Fang, Zihao, et al.
Pubblicazione: (2026)

MFA-KWS: Effective Keyword Spotting with Multi-head Frame-asynchronous Decoding
di: Xi, Yu, et al.
Pubblicazione: (2025)

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding
di: Wei, Linye, et al.
Pubblicazione: (2025)

Extending Whisper with prompt tuning to target-speaker ASR
di: Ma, Hao, et al.
Pubblicazione: (2023)

Whisper-PMFA: Partial Multi-Scale Feature Aggregation for Speaker Verification using Whisper Models
di: Zhao, Yiyang, et al.
Pubblicazione: (2024)

HebDB: a Weakly Supervised Dataset for Hebrew Speech Processing
di: Turetzky, Arnon, et al.
Pubblicazione: (2024)

Overcoming Data Scarcity in Multi-Dialectal Arabic ASR via Whisper Fine-Tuning
di: Özyilmaz, Ömer Tarik, et al.
Pubblicazione: (2025)

Resource-Efficient Adaptation of Speech Foundation Models for Multi-Speaker ASR
di: Wang, Weiqing, et al.
Pubblicazione: (2024)

Bangla-WhisperDiar: Fine-Tuning Whisper and PyAnnote for Bangla Long-Form Speech Recognition and Speaker Diarization
di: Bhuiyan, Mohammed Aman, et al.
Pubblicazione: (2026)

Unifying Streaming and Non-streaming Zipformer-based ASR
di: Sharma, Bidisha, et al.
Pubblicazione: (2025)

Loss Masking Is Not Needed in Decoder-only Transformer for Discrete-token-based ASR
di: Chen, Qian, et al.
Pubblicazione: (2023)

Model-free Speculative Decoding for Transformer-based ASR with Token Map Drafting
di: Ho, Tuan Vu, et al.
Pubblicazione: (2025)

Deepfake Detection of Singing Voices With Whisper Encodings
di: Sharma, Falguni, et al.
Pubblicazione: (2025)

Explore the Reinforcement Learning for the LLM based ASR and TTS system
di: Gao, Changfeng, et al.
Pubblicazione: (2025)

Towards Rehearsal-Free Multilingual ASR: A LoRA-based Case Study on Whisper
di: Xu, Tianyi, et al.
Pubblicazione: (2024)

Whisper-RIR-Mega: A Paired Clean-Reverberant Speech Benchmark for ASR Robustness to Room Acoustics
di: Goswami, Mandip
Pubblicazione: (2026)

Enhanced ASR Robustness to Packet Loss with a Front-End Adaptation Network
di: Dissen, Yehoshua, et al.
Pubblicazione: (2024)

Whisper-SV: Adapting Whisper for Low-data-resource Speaker Verification
di: Zhang, Li, et al.
Pubblicazione: (2024)

Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whisper
di: Thorbecke, Iuliia, et al.
Pubblicazione: (2024)