paper-with-me

Papers

Transformer in action: a comparative study of transformer-based acoustic models for large scale speech recognition applications

2020-10-27 · Yongqiang Wang, Yangyang Shi, Frank Zhang, Chunyang Wu, Julian Chan, Ching-Feng Yeh, Alex Xiao

In this paper, we summarize the application of transformer and its streamable variant, Emformer based acoustic model for large scale speech recognition applications. We compare the transformer based acoustic models with their LSTM counterparts on industrial scale tasks. Specifically, we compare Emformer with latency-controlled BLSTM (LCBLSTM) on medium latency tasks and LSTM on low latency tasks. On a low latency voice assistant task, Emformer gets 24% to 26% relative word error rate reductions (WERRs). For medium latency scenarios, comparing with LCBLSTM with similar model size and latency, Emformer gets significant WERR across four languages in video captioning datasets with 2-3 times inference real-time factors reduction.

📄 PDF Abstract BibTeX arXiv:2010.14665

Code (0)

등록된 구현이 없습니다.

Tasks

speech-recognitionSpeech RecognitionVideo Captioning

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

State Space Models for Bioacoustics: A Comparative Evaluation with Transformers

2025-12-03 · Chengyu Tang, Sanjeev Baskiyar arxiv

In this study, we evaluate the efficacy of the Mamba architecture bioacoustics by introducing BioMamba, a Mamba-based audio representation model for wildlife sounds. We pre-train a BioMamba using self-supervised learning…

Self-Supervised Learning

Active Bird2Vec: Towards End-to-End Bird Sound Monitoring with Transformers

2023-08-14 · Lukas Rauch, Raphael Schwinger, Moritz Wirth, Bernhard Sick 외

We propose a shift towards end-to-end learning in bird sound monitoring by combining self-supervised (SSL) and deep active learning (DAL). Leveraging transformer models, we aim to bypass traditional spectrogram conversio…

Active LearningDecision Making

A Comparative Study on Code Generation with Transformers

2024-12-07 · Namrata Das, Rakshya Panta, Neelam Karki, Ruchi Manandhar 외

In an era of widespread influence of Natural Language Processing (NLP), there have been multiple research efforts to supplant traditional manual coding techniques with automated systems capable of generating solutions au…

Code Generation

A Transformer with Interleaved Self-attention and Convolution for Hybrid Acoustic Models

2019-10-23 · Liang Lu

Transformer with self-attention has achieved great success in the area of nature language processing. Recently, there have been a few studies on transformer for end-to-end speech recognition, while its application for hy…

speech-recognitionSpeech Recognition

Transformer-based Acoustic Modeling for Hybrid Speech Recognition

2019-10-22 · Yongqiang Wang, Abdel-rahman Mohamed, Duc Le, Chunxi Liu 외

We propose and evaluate transformer-based acoustic models (AMs) for hybrid speech recognition. Several modeling choices are discussed in this work, including various positional embedding methods and an iterated loss to e…

Language ModelingLanguage Modellingspeech-recognitionSpeech Recognition