paper-with-me

홈 › Papers

Nana-HDR: A Non-attentive Non-autoregressive Hybrid Model for TTS

2021-09-28 · Shilun Lin, Wenchao Su, Li Meng, Fenglong Xie, Xinhui Li, Li Lu

This paper presents Nana-HDR, a new non-attentive non-autoregressive model with hybrid Transformer-based Dense-fuse encoder and RNN-based decoder for TTS. It mainly consists of three parts: Firstly, a novel Dense-fuse encoder with dense connections between basic Transformer blocks for coarse feature fusion and a multi-head attention layer for fine feature fusion. Secondly, a single-layer non-autoregressive RNN-based decoder. Thirdly, a duration predictor instead of an attention model that connects the above hybrid encoder and decoder. Experiments indicate that Nana-HDR gives full play to the advantages of each component, such as strong text encoding ability of Transformer-based encoder, stateful decoding without being bothered by exposure bias and local information preference, and stable alignment provided by duration predictor. Due to these advantages, Nana-HDR achieves competitive performance in naturalness and robustness on two Mandarin corpora.

📄 PDF Abstract BibTeX arXiv:2109.13673

Code (0)

등록된 구현이 없습니다.

Tasks

Decoder

Methods 이 논문이 사용한 방법론

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…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
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…
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…

Similar Papers 제목 키워드 기반

uOttawa at SemEval-2018 Task 1: Self-Attentive Hybrid GRU-Based Network

2018-06-01 · SEMEVAL 2018 6 · Ahmed Husseini Orabi, Mahmoud Husseini Orabi, Diana Inkpen, David Van Bruwaene

We propose a novel attentive hybrid GRU-based network (SAHGN), which we used at SemEval-2018 Task 1: Affect in Tweets. Our network has two main characteristics, 1) has the ability to internally optimize its feature repre…

regression

Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech Recognition

2020-05-11 · Ye Bai, Jiangyan Yi, Jian-Hua Tao, Zhengkun Tian 외

Although attention based end-to-end models have achieved promising performance in speech recognition, the multi-pass forward computation in beam-search increases inference time cost, which limits their practical applicat…

Sentencespeech-recognitionSpeech Recognition

Symbiotic Hybrid Neural Network Watchdog For Outlier Detection

2021-02-28 · Justin Bui, Robert J. Marks II

Neural networks are largely black boxes. A neural network trained to classify fruit may classify a picture of a giraffe as a banana. A neural network watchdog's job is to identify such inputs, allowing a classifier to di…

Outlier Detection

Banana Sub-Family Classification and Quality Prediction using Computer Vision

2022-04-06 · Narayana Darapaneni, Arjun Tanndalam, Mohit Gupta, Neeta Taneja 외

India is the second largest producer of fruits and vegetables in the world, and one of the largest consumers of fruits like Banana, Papaya and Mangoes through retail and ecommerce giants like BigBasket, Grofers and Amazo…

ClassificationData Augmentationimage-classificationImage Classification+2

Eigenanalysis framework for autoregressive neural emulators of multi-scale chaotic dynamics

2026-08-17 · Conrad Ainslie, Pedram Hassanzadeh, Michael W. Mahoney, Ashesh Chattopadhyay arxiv

Neural autoregressive models have rapidly emerged as powerful emulators of high-dimensional chaotic systems, yet their long-term instability and error growth remain poorly understood, leading to ad-hoc solutions. Here, w…