Copertina

Training and Inference Efficiency of Encoder-Decoder Speech Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Żelasko, Piotr, Dhawan, Kunal, Galvez, Daniel, Puvvada, Krishna C., Pasad, Ankita, Koluguri, Nithin Rao, Hu, Ke, Lavrukhin, Vitaly, Balam, Jagadeesh, Ginsburg, Boris
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Audio and Speech Processing
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Less is More: Accurate Speech Recognition & Translation without Web-Scale Data
di: Puvvada, Krishna C., et al.
Pubblicazione: (2024)

Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations
di: Dhawan, Kunal, et al.
Pubblicazione: (2024)

NEST: Self-supervised Fast Conformer as All-purpose Seasoning to Speech Processing Tasks
di: Huang, He, et al.
Pubblicazione: (2024)

BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5
di: Chen, Zhehuai, et al.
Pubblicazione: (2024)

Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems
di: Park, Taejin, et al.
Pubblicazione: (2024)

VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Text Supervised Fine-Tuning
di: Peng, Yifan, et al.
Pubblicazione: (2024)

Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST
di: Sekoyan, Monica, et al.
Pubblicazione: (2025)

EMMeTT: Efficient Multimodal Machine Translation Training
di: Żelasko, Piotr, et al.
Pubblicazione: (2024)

Speaker Targeting via Self-Speaker Adaptation for Multi-talker ASR
di: Wang, Weiqing, et al.
Pubblicazione: (2025)

META-CAT: Speaker-Informed Speech Embeddings via Meta Information Concatenation for Multi-talker ASR
di: Wang, Jinhan, et al.
Pubblicazione: (2024)

Longer is (Not Necessarily) Stronger: Punctuated Long-Sequence Training for Enhanced Speech Recognition and Translation
di: Koluguri, Nithin Rao, et al.
Pubblicazione: (2024)

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

Word Level Timestamp Generation for Automatic Speech Recognition and Translation
di: Hu, Ke, et al.
Pubblicazione: (2025)

Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer
di: Burchi, Maxime, et al.
Pubblicazione: (2024)

Spectral Codecs: Improving Non-Autoregressive Speech Synthesis with Spectrogram-Based Audio Codecs
di: Langman, Ryan, et al.
Pubblicazione: (2024)

Flexible Multichannel Speech Enhancement for Noise-Robust Frontend
di: Jukić, Ante, et al.
Pubblicazione: (2024)

Granary: Speech Recognition and Translation Dataset in 25 European Languages
di: Koluguri, Nithin Rao, et al.
Pubblicazione: (2025)

Schrödinger Bridge for Generative Speech Enhancement
di: Jukić, Ante, et al.
Pubblicazione: (2024)

Label-Looping: Highly Efficient Decoding for Transducers
di: Bataev, Vladimir, et al.
Pubblicazione: (2024)

Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition
di: Noroozi, Vahid, et al.
Pubblicazione: (2023)

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model
di: Hu, Ke, et al.
Pubblicazione: (2025)

What do Speech Foundation Models Learn? Analysis and Applications
di: Pasad, Ankita
Pubblicazione: (2025)

Streaming Sortformer: Speaker Cache-Based Online Speaker Diarization with Arrival-Time Ordering
di: Medennikov, Ivan, et al.
Pubblicazione: (2025)

Chain-of-Thought Prompting for Speech Translation
di: Hu, Ke, et al.
Pubblicazione: (2024)

Open Automatic Speech Recognition Models for Classical and Modern Standard Arabic
di: Grigoryan, Lilit, et al.
Pubblicazione: (2025)

SPGISpeech 2.0: Transcribed multi-speaker financial audio for speaker-tagged transcription
di: Grossman, Raymond, et al.
Pubblicazione: (2025)

Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation
di: Srivastav, Vaibhav, et al.
Pubblicazione: (2025)

Pushing the Limits of Beam Search Decoding for Transducer-based ASR models
di: Grigoryan, Lilit, et al.
Pubblicazione: (2025)

FlexCTC: GPU-powered CTC Beam Decoding With Advanced Contextual Abilities
di: Grigoryan, Lilit, et al.
Pubblicazione: (2025)

Instruction Data Generation and Unsupervised Adaptation for Speech Language Models
di: Noroozi, Vahid, et al.
Pubblicazione: (2024)

NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding
di: Bataev, Vladimir, et al.
Pubblicazione: (2025)

TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Tree
di: Andrusenko, Andrei, et al.
Pubblicazione: (2025)

Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator
di: Bataev, Vladimir, et al.
Pubblicazione: (2023)

Methods to Increase the Amount of Data for Speech Recognition for Low Resource Languages
di: Ayrapetyan, Alexan, et al.
Pubblicazione: (2025)

Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter
di: Andrusenko, Andrei, et al.
Pubblicazione: (2024)

NeKo: Cross-Modality Post-Recognition Error Correction with Tasks-Guided Mixture-of-Experts Language Model
di: Lin, Yen-Ting, et al.
Pubblicazione: (2024)

DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data
di: Lu, Ke-Han, et al.
Pubblicazione: (2024)

What Do Self-Supervised Speech Models Know About Words?
di: Pasad, Ankita, et al.
Pubblicazione: (2023)

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization
di: Andrusenko, Andrei, et al.
Pubblicazione: (2026)

TTS-Transducer: End-to-End Speech Synthesis with Neural Transducer
di: Bataev, Vladimir, et al.
Pubblicazione: (2025)