paper-with-me

Papers

Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition

2021-12-10 · Kenichi Kumatani, Robert Gmyr, Felipe Cruz Salinas, Linquan Liu, Wei Zuo, Devang Patel, Eric Sun, Yu Shi

The sparsely-gated Mixture of Experts (MoE) can magnify a network capacity with a little computational complexity. In this work, we investigate how multi-lingual Automatic Speech Recognition (ASR) networks can be scaled up with a simple routing algorithm in order to achieve better accuracy. More specifically, we apply the sparsely-gated MoE technique to two types of networks: Sequence-to-Sequence Transformer (S2S-T) and Transformer Transducer (T-T). We demonstrate through a set of ASR experiments on multiple language data that the MoE networks can reduce the relative word error rates by 16.3% and 4.6% with the S2S-T and T-T, respectively. Moreover, we thoroughly investigate the effect of the MoE on the T-T architecture in various conditions: streaming mode, non-streaming mode, the use of language ID and the label decoder with the MoE.

📄 PDF Abstract BibTeX arXiv:2112.05820

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderMixture-of-Expertsspeech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
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…
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…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Distilling Efficient Language-Specific Models for Cross-Lingual Transfer

2023-06-02 · Alan Ansell, Edoardo Maria Ponti, Anna Korhonen, Ivan Vulić

Massively multilingual Transformers (MMTs), such as mBERT and XLM-R, are widely used for cross-lingual transfer learning. While these are pretrained to represent hundreds of languages, end users of NLP systems are often …

Cross-Lingual TransferTransfer LearningXLM-RZero-Shot Cross-Lingual Transfer

High-Resolution Building and Road Detection from Sentinel-2

2023-10-17 · Wojciech Sirko, Emmanuel Asiedu Brempong, Juliana T. C. Marcos, Abigail Annkah 외

Mapping buildings and roads automatically with remote sensing typically requires high-resolution imagery, which is expensive to obtain and often sparsely available. In this work we demonstrate how multiple 10 m resolutio…

Road SegmentationSegmentation

XL-NBT: A Cross-lingual Neural Belief Tracking Framework

2018-08-19 · EMNLP 2018 10 · Wenhu Chen, Jianshu Chen, Yu Su, Xin Wang 외

Task-oriented dialog systems are becoming pervasive, and many companies heavily rely on them to complement human agents for customer service in call centers. With globalization, the need for providing cross-lingual custo…

Transfer Learning

DistilXLSR: A Light Weight Cross-Lingual Speech Representation Model

2023-06-02 · Haoyu Wang, Siyuan Wang, Wei-Qiang Zhang, Jinfeng Bai

Multilingual self-supervised speech representation models have greatly enhanced the speech recognition performance for low-resource languages, and the compression of these huge models has also become a crucial prerequisi…

speech-recognitionSpeech Recognition

Towards Better Monolingual Japanese Retrievers with Multi-Vector Models

2023-12-26 · Benjamin Clavié

As language-specific training data tends to be sparsely available compared to English, document retrieval in many languages has been largely relying on multilingual models. In Japanese, the best performing deep-learning …

AllRetrieval