paper-with-me

Papers

Transformer-based Acoustic Modeling for Hybrid Speech Recognition

2019-10-22 · Yongqiang Wang, Abdel-rahman Mohamed, Duc Le, Chunxi Liu, Alex Xiao, Jay Mahadeokar, Hongzhao Huang, Andros Tjandra, Xiaohui Zhang, Frank Zhang, Christian Fuegen, Geoffrey Zweig, Michael L. Seltzer

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.

📄 PDF Abstract BibTeX arXiv:1910.09799

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modellingspeech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

AM 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

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

RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation

2019-05-08 · Christoph Lüscher, Eugen Beck, Kazuki Irie, Markus Kitza 외

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+3

Improving Hybrid CTC/Attention End-to-end Speech Recognition with Pretrained Acoustic and Language Model

2021-12-14 · Keqi Deng, Songjun Cao, Yike Zhang, Long Ma

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+3

Toward Cross-Domain Speech Recognition with End-to-End Models

2020-03-09 · Thai-Son Nguyen, Sebastian Stüker, Alex Waibel

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 Recognition

Towards End-to-End Code-Switching Speech Recognition

2018-10-31 · Ne Luo, Dongwei Jiang, Shuaijiang Zhao, Caixia Gong 외

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