Transformer-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 enable training deep transformers. We also present a preliminary study of using limited right context in transformer models, which makes it possible for streaming applications. We demonstrate that on the widely used Librispeech benchmark, our transformer-based AM outperforms the best published hybrid result by 19% to 26% relative when the standard n-gram language model (LM) is used. Combined with neural network LM for rescoring, our proposed approach achieves state-of-the-art results on Librispeech. Our findings are also confirmed on a much larger internal dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage Modellingspeech-recognitionSpeech RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A 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 RecognitionRWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation
We present state-of-the-art automatic speech recognition (ASR) systems employing a standard hybrid DNN/HMM architecture compared to an attention-based encoder-decoder design for the LibriSpeech task. Detailed description…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderLanguage Modeling+3Improving Hybrid CTC/Attention End-to-end Speech Recognition with Pretrained Acoustic and Language Model
Recently, self-supervised pretraining has achieved impressive results in end-to-end (E2E) automatic speech recognition (ASR). However, the dominant sequence-to-sequence (S2S) E2E model is still hard to fully utilize the …
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderLanguage Modeling+3Toward Cross-Domain Speech Recognition with End-to-End Models
In the area of multi-domain speech recognition, research in the past focused on hybrid acoustic models to build cross-domain and domain-invariant speech recognition systems. In this paper, we empirically examine the diff…
speech-recognitionSpeech RecognitionTowards End-to-End Code-Switching Speech Recognition
Code-switching speech recognition has attracted an increasing interest recently, but the need for expert linguistic knowledge has always been a big issue. End-to-end automatic speech recognition (ASR) simplifies the buil…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language Identificationspeech-recognition+1