Image de couverture de livre

HAINAN: Fast and Accurate Transducer for Hybrid-Autoregressive ASR

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xu, Hainan, Bartley, Travis M., Bataev, Vladimir, Ginsburg, Boris
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Chunk-wise Attention Transducers for Fast and Accurate Streaming Speech-to-Text
par: Xu, Hainan, et autres
Publié: (2026)

Pushing the Limits of Beam Search Decoding for Transducer-based ASR models
par: Grigoryan, Lilit, et autres
Publié: (2025)

Label-Looping: Highly Efficient Decoding for Transducers
par: Bataev, Vladimir, et autres
Publié: (2024)

Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter
par: Andrusenko, Andrei, et autres
Publié: (2024)

WIND: Accelerated RNN-T Decoding with Windowed Inference for Non-blank Detection
par: Xu, Hainan, et autres
Publié: (2025)

Transducers with Pronunciation-aware Embeddings for Automatic Speech Recognition
par: Xu, Hainan, et autres
Publié: (2024)

Multi-blank Transducers for Speech Recognition
par: Xu, Hainan, et autres
Publié: (2022)

RNN-Transducer-based Losses for Speech Recognition on Noisy Targets
par: Bataev, Vladimir
Publié: (2025)

Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator
par: Bataev, Vladimir, et autres
Publié: (2023)

Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPU
par: Galvez, Daniel, et autres
Publié: (2024)

NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding
par: Bataev, Vladimir, et autres
Publié: (2025)

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization
par: Andrusenko, Andrei, et autres
Publié: (2026)

FlexCTC: GPU-powered CTC Beam Decoding With Advanced Contextual Abilities
par: Grigoryan, Lilit, et autres
Publié: (2025)

TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Tree
par: Andrusenko, Andrei, et autres
Publié: (2025)

TTS-Transducer: End-to-End Speech Synthesis with Neural Transducer
par: Bataev, Vladimir, et autres
Publié: (2025)

Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations
par: Dhawan, Kunal, et autres
Publié: (2024)

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

Longer is (Not Necessarily) Stronger: Punctuated Long-Sequence Training for Enhanced Speech Recognition and Translation
par: Koluguri, Nithin Rao, et autres
Publié: (2024)

TDT-KWS: Fast And Accurate Keyword Spotting Using Token-and-duration Transducer
par: Xi, Yu, et autres
Publié: (2024)

Star Attention: Efficient LLM Inference over Long Sequences
par: Acharya, Shantanu, et autres
Publié: (2024)

Fast and Interpretable Autoregressive Estimation with Neural Network Backpropagation
par: Lucena, Anaísa, et autres
Publié: (2026)

Transformers as Transducers
par: Strobl, Lena, et autres
Publié: (2024)

Fast and Accurate Probing of In-Training LLMs' Downstream Performances
par: Liu, Zhichen, et autres
Publié: (2026)

Fast Graph Generation via Autoregressive Noisy Filtration Modeling
par: Krimmel, Markus, et autres
Publié: (2025)

Transduce: learning transduction grammars for string transformation
par: Frydman, Francis, et autres
Publié: (2023)

nGPT: Normalized Transformer with Representation Learning on the Hypersphere
par: Loshchilov, Ilya, et autres
Publié: (2024)

Fast, Accurate and Interpretable Graph Classification with Topological Kernels
par: Wesołowski, Adam, et autres
Publié: (2025)

Retrieval from Within: An Intrinsic Capability of Attention-Based Models
par: Hoffer, Elad, et autres
Publié: (2026)

Normalized Architectures are Natively 4-Bit
par: Fishman, Maxim, et autres
Publié: (2026)

Workspace Optimization: How to Train Your Agent
par: Sarafian, Elad, et autres
Publié: (2026)

Rock the KASBA: Blazingly Fast and Accurate Time Series Clustering
par: Holder, Christopher, et autres
Publié: (2024)

FASP: Fast and Accurate Structured Pruning of Large Language Models
par: Hu, Hanyu, et autres
Publié: (2025)

Asynchronous Sharpness-Aware Minimization For Fast and Accurate Deep Learning
par: Jo, Junhyuk, et autres
Publié: (2025)

Fast Autoregressive Models for Continuous Latent Generation
par: Hang, Tiankai, et autres
Publié: (2025)

Generalizable, Fast, and Accurate DeepQSPR with fastprop
par: Burns, Jackson, et autres
Publié: (2024)

Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST
par: Sekoyan, Monica, et autres
Publié: (2025)

Towards Model-Agnostic Posterior Approximation for Fast and Accurate Variational Autoencoders
par: Yacoby, Yaniv, et autres
Publié: (2024)

Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction
par: Willette, Jeffrey, et autres
Publié: (2025)

Fast and Accurate Graph Learning for Huge Data via Minipatch Ensembles
par: Yao, Tianyi, et autres
Publié: (2021)

Parameter Importance-Driven Continual Learning for Foundation Models
par: Wang, Lingxiang, et autres
Publié: (2025)