paper-with-me

Papers

Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment

2018-04-30 · NAACL 2018 6 · Gonzalo Iglesias, William Tambellini, Adrià De Gispert, Eva Hasler, Bill Byrne

We describe a batched beam decoding algorithm for NMT with LMBR n-gram posteriors, showing that LMBR techniques still yield gains on top of the best recently reported results with Transformers. We also discuss acceleration strategies for deployment, and the effect of the beam size and batching on memory and speed.

📄 PDF Abstract BibTeX arXiv:1804.11324

Code (0)

등록된 구현이 없습니다.

Tasks

NMT

Similar Papers 제목 키워드 기반

A Streaming Approach For Efficient Batched Beam Search

2020-10-05 · EMNLP 2020 11 · Kevin Yang, Violet Yao, John DeNero, Dan Klein

We propose an efficient batching strategy for variable-length decoding on GPU architectures. During decoding, when candidates terminate or are pruned according to heuristics, our streaming approach periodically "refills"…

GPUMachine TranslationTranslation

Beam Search Decoding using Manner of Articulation Detection Knowledge Derived from Connectionist Temporal Classification

2018-11-16 · Pradeep Rangan, Sreenivasa Rao K

Manner of articulation detection using deep neural networks require a priori knowledge of the attribute discriminative features or the decent phoneme alignments. However generating an appropriate phoneme alignment is com…

AttributeGeneral ClassificationManner Of Articulation Detection

FlexCTC: GPU-powered CTC Beam Decoding With Advanced Contextual Abilities

2025-08-10 · Lilit Grigoryan, Vladimir Bataev, Nikolay Karpov, Andrei Andrusenko 외 arxiv

While beam search improves speech recognition quality over greedy decoding, standard implementations are slow, often sequential, and CPU-bound. To fully leverage modern hardware capabilities, we present a novel open-sour…

Speech Recognition

WIND: Accelerated RNN-T Decoding with Windowed Inference for Non-blank Detection

2025-05-19 · Hainan Xu, Vladimir Bataev, Lilit Grigoryan, Boris Ginsburg

We propose Windowed Inference for Non-blank Detection (WIND), a novel strategy that significantly accelerates RNN-T inference without compromising model accuracy. During model inference, instead of processing frames sequ…

TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems

2026-08-21 · Vladimir Bataev, Lilit Grigoryan, Andrei Andrusenko, Nikolay Karpov 외 arxiv

Contextualization is essential for production automatic speech recognition (ASR) systems, where user-provided phrases must be recognized accurately under strict latency constraints. Although many context-biasing methods …

Speech Recognition