Transformer in action: a comparative study of transformer-based acoustic models for large scale speech recognition applications
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.
Code (0)
등록된 구현이 없습니다.
Tasks
speech-recognitionSpeech RecognitionVideo CaptioningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
State Space Models for Bioacoustics: A Comparative Evaluation with Transformers
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 LearningActive Bird2Vec: Towards End-to-End Bird Sound Monitoring with Transformers
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 MakingA Comparative Study on Code Generation with Transformers
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 GenerationA Transformer with Interleaved Self-attention and Convolution for Hybrid Acoustic Models
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 RecognitionTransformer-based Acoustic Modeling for Hybrid Speech Recognition
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