paper-with-me

Papers

Loss Masking Is Not Needed in Decoder-only Transformer for Discrete-token-based ASR

2023-11-08 · Qian Chen, Wen Wang, Qinglin Zhang, Siqi Zheng, Shiliang Zhang, Chong Deng, Yukun Ma, Hai Yu, Jiaqing Liu, Chong Zhang

Recently, unified speech-text models, such as SpeechGPT, VioLA, and AudioPaLM, have achieved remarkable performance on various speech tasks. These models discretize speech signals into tokens (speech discretization) and use a shared vocabulary for both text and speech tokens. Then they train a single decoder-only Transformer on a mixture of speech tasks. However, these models rely on the Loss Masking strategy for the ASR task, which ignores the dependency among speech tokens. In this paper, we propose to model speech tokens in an autoregressive way, similar to text. We find that applying the conventional cross-entropy loss on input speech tokens does not consistently improve the ASR performance over the Loss Masking approach. To address this issue, we propose a novel approach denoted Smoothed Label Distillation (SLD), which applies a KL divergence loss with smoothed labels on speech tokens. Our experiments show that SLD effectively models speech tokens and outperforms Loss Masking for decoder-only Transformers in ASR tasks with different speech discretization methods. The source code can be found here: https://github.com/alibaba-damo-academy/SpokenNLP/tree/main/sld

📄 PDF Abstract BibTeX arXiv:2311.04534

Code (1)

alibaba-damo-academy/spokennlp 공식 구현 tf

Tasks

Decoder

Methods 이 논문이 사용한 방법론

Attention 설명 없음
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…
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…
Residual Connection 설명 없음
Multi-Head Attention 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…
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…

Similar Papers 제목 키워드 기반

Hybrid Mamba-Transformer Decoder for Error-Correcting Codes

2025-05-23 · Shy-el Cohen, Yoni Choukroun, Eliya Nachmani

We introduce a novel deep learning method for decoding error correction codes based on the Mamba architecture, enhanced with Transformer layers. Our approach proposes a hybrid decoder that leverages Mamba's efficient seq…

DecoderMamba

Attention Head Masking for Inference Time Content Selection in Abstractive Summarization

2021-04-06 · NAACL 2021 4 · Shuyang Cao, Lu Wang

How can we effectively inform content selection in Transformer-based abstractive summarization models? In this work, we present a simple-yet-effective attention head masking technique, which is applied on encoder-decoder…

Abstractive Text SummarizationDecoderDocument Summarization

Accelerating Neural Transformer via an Average Attention Network

2018-05-02 · ACL 2018 7 · Biao Zhang, Deyi Xiong, Jinsong Su

With parallelizable attention networks, the neural Transformer is very fast to train. However, due to the auto-regressive architecture and self-attention in the decoder, the decoding procedure becomes slow. To alleviate …

DecoderMachine TranslationTranslation

A Mixture of Experts Vision Transformer for High-Fidelity Surface Code Decoding

2026-01-18 · Hoang Viet Nguyen, Manh Hung Nguyen, Hoang Ta, Van Khu Vu 외 arxiv

Quantum error correction is a key ingredient for large scale quantum computation, protecting logical information from physical noise by encoding it into many physical qubits. Topological stabilizer codes are particularly…

Masked Autoencoders that Listen

2022-07-13 · Po-Yao Huang, Hu Xu, Juncheng Li, Alexei Baevski 외

This paper studies a simple extension of image-based Masked Autoencoders (MAE) to self-supervised representation learning from audio spectrograms. Following the Transformer encoder-decoder design in MAE, our Audio-MAE fi…

Audio ClassificationDecoderRepresentation LearningSpeaker Identification