English
Related papers

Related papers: Compound Word Transformer: Learning to Compose Ful…

200 papers

Neural end-to-end text-to-speech (TTS) , which adopts either a recurrent model, e.g. Tacotron, or an attention one, e.g. Transformer, to characterize a speech utterance, has achieved significant improvement of speech synthesis. However, it…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-18 Xi Wang , Huaiping Ming , Lei He , Frank K. Soong

Character-level language models obviate the need for separately trained tokenizers, but efficiency suffers from longer sequence lengths. Learning to combine character representations into tokens has made training these models more…

Computation and Language · Computer Science 2023-11-16 William Fleshman , Benjamin Van Durme

Neural networks using numerous text data have been successfully applied to a variety of tasks. While massive text data is usually compressed using techniques such as grammar compression, almost all of the previous machine learning methods…

Machine Learning · Statistics 2020-03-02 Yoichi Sasaki , Kosuke Akimoto , Takanori Maehara

Recent diagnostic datasets on compositional generalization, such as SCAN (Lake and Baroni, 2018) and COGS (Kim and Linzen, 2020), expose severe problems in models trained from scratch on these datasets. However, in contrast to this poor…

Computation and Language · Computer Science 2023-11-09 Xiang Zhou , Yichen Jiang , Mohit Bansal

We introduce VampNet, a masked acoustic token modeling approach to music synthesis, compression, inpainting, and variation. We use a variable masking schedule during training which allows us to sample coherent music from the model by…

Sound · Computer Science 2023-07-13 Hugo Flores Garcia , Prem Seetharaman , Rithesh Kumar , Bryan Pardo

Transformers have seen an unprecedented rise in Natural Language Processing and Computer Vision tasks. However, in audio tasks, they are either infeasible to train due to extremely large sequence length of audio waveforms or incur a…

Machine Learning · Computer Science 2022-02-02 Surya Kant Sahu , Sai Mitheran , Juhi Kamdar , Meet Gandhi

Transformer models are not only successful in natural language processing (NLP) but also demonstrate high potential in computer vision (CV). Despite great advance, most of works only focus on improvement of architectures but pay little…

Computer Vision and Pattern Recognition · Computer Science 2021-12-21 Jiangtao Xie , Ruiren Zeng , Qilong Wang , Ziqi Zhou , Peihua Li

Ever since their conception, Transformers have taken over traditional sequence models in many tasks, such as NLP, image classification, and video/audio processing, for their fast training and superior performance. Much of the merit is…

Machine Learning · Computer Science 2023-02-17 Hongyu Hè , Marko Kabic

Flexible neural sequence models outperform grammar- and automaton-based counterparts on a variety of tasks. However, neural models perform poorly in settings requiring compositional generalization beyond the training data -- particularly to…

Computation and Language · Computer Science 2021-06-09 Ekin Akyürek , Afra Feyza Akyürek , Jacob Andreas

Recently, Transformer-based encoder-decoder models have demonstrated strong performance in multilingual speech recognition. However, the decoder's autoregressive nature and large size introduce significant bottlenecks during inference.…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-28 Yunkyu Lim , Jihwan Park , Hyung Yong Kim , Hanbin Lee , Byeong-Yeol Kim

While sequence-to-sequence models have shown remarkable generalization power across several natural language tasks, their construct of solutions are argued to be less compositional than human-like generalization. In this paper, we present…

Computation and Language · Computer Science 2019-06-07 Kris Korrel , Dieuwke Hupkes , Verna Dankers , Elia Bruni

At present, neural network models show powerful sequence prediction ability and are used in many automatic composition models. In comparison, the way humans compose music is very different from it. Composers usually start by creating…

Sound · Computer Science 2024-10-18 Yutian Wang , Wanyin Yang , Zhenrong Dai , Yilong Zhang , Kun Zhao , Hui Wang

We propose a new encoder-decoder approach to learn distributed sentence representations that are applicable to multiple purposes. The model is learned by using a convolutional neural network as an encoder to map an input sentence into a…

Computation and Language · Computer Science 2017-07-28 Zhe Gan , Yunchen Pu , Ricardo Henao , Chunyuan Li , Xiaodong He , Lawrence Carin

Encoder transformer models compress information from all tokens in a sequence into a single [CLS] token to represent global context. This approach risks diluting fine-grained or hierarchical features, leading to information loss in…

Computation and Language · Computer Science 2025-09-23 Asif Shahriar , Rifat Shahriyar , M Saifur Rahman

In this paper, we propose a novel design for AI-native goal-oriented communications, exploiting transformer neural networks under dynamic inference constraints on bandwidth and computation. Transformers have become the standard architecture…

Information Theory · Computer Science 2024-05-07 Alessio Devoto , Simone Petruzzi , Jary Pomponi , Paolo Di Lorenzo , Simone Scardapane

Existing methods for expressive music performance rendering rely on supervised learning over small labeled datasets, which limits scaling of both data volume and model size, despite the availability of vast unlabeled music, as in vision and…

Sound · Computer Science 2025-12-03 Hong-Jie You , Jie-Jing Shao , Xiao-Wen Yang , Lin-Han Jia , Lan-Zhe Guo , Yu-Feng Li

Creating a pop song melody according to pre-written lyrics is a typical practice for composers. A computational model of how lyrics are set as melodies is important for automatic composition systems, but an end-to-end lyric-to-melody model…

Audio and Speech Processing · Electrical Eng. & Systems 2023-01-05 Daiyu Zhang , Ju-Chiang Wang , Katerina Kosta , Jordan B. L. Smith , Shicen Zhou

Transformer-based models have achieved state-of-the-art results in many natural language processing tasks. The self-attention architecture allows transformer to combine information from all elements of a sequence into context-aware…

Computation and Language · Computer Science 2021-02-17 Mikhail S. Burtsev , Yuri Kuratov , Anton Peganov , Grigory V. Sapunov

It is well understood that different neural network architectures are suited to different tasks, but is there always a single best architecture for a given task? We compare the expressive power of transformers, RNNs, and transformers with…

Machine Learning · Computer Science 2026-01-29 Gilad Yehudai , Noah Amsel , Joan Bruna

Convolutional neural networks (CNNs) have been successfully applied on both discriminative and generative modeling for music-related tasks. For a particular task, the trained CNN contains information representing the decision making or the…

Sound · Computer Science 2017-06-30 S. Geng , G. Ren , M. Ogihara
‹ Prev 1 8 9 10 Next ›