paper-with-me

홈 › Papers

Conditioning Sequence-to-sequence Networks with Learned Activations

2021-09-29 · ICLR 2022 4 · Alberto Gil Couto Pimentel Ramos, Abhinav Mehrotra, Nicholas Donald Lane, Sourav Bhattacharya

Conditional neural networks play an important role in a number of sequence-to-sequence modeling tasks, including personalized sound enhancement (PSE), speaker dependent automatic speech recognition (ASR), and generative modeling such as text-to-speech synthesis. In conditional neural networks, the output of a model is often influenced by a conditioning vector, in addition to the input. Common approaches of conditioning include input concatenation or modulation with the conditioning vector, which comes at the cost of increased model size.In this work, we introduce a novel approach of neural network conditioning by learning intermediate layer activations based on the conditioning vector. We systematically explore and show that learned activations can produce conditional models with comparable or better quality, while having significantly lower sizes, thus making them ideal candidates for resource-efficient on-device deployment. As exemplary target use-cases we consider (i) the task of PSE as a pre-processing technique for improving telephony or pre-trained ASR performance under babble or ambient noise, and (ii) personalized ASR in single speaker scenarios. We find that conditioning via activation learning is an effective modeling strategy, suggesting a broad applicability of the proposed technique across a number of application domains.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionSpeech Synthesistext-to-speechText to SpeechText-To-Speech Synthesis

Similar Papers 제목 키워드 기반

Prompt Compression via Activation Aggregation

2026-07-09 · Thibaud Ardoin, Semira Einsele, Evis Bregu, Gerhard Wunder arxiv

Large language models process prompts by propagating activations through dozens of layers before generating a response. We ask whether the task-relevant information contained in an instruction prompt can be compressed in…

SiDGen: Structure-informed Diffusion for Generative modeling of Ligands for Proteins

2025-11-12 · Samyak Sanghvi, Nishant Ranjan, Tarak Karmakar arxiv

Structure-based drug design (SBDD) faces a fundamental scaling fidelity dilemma: rich pocket-aware conditioning captures interaction geometry but can be costly, often scales quadratically ($O(L^2)$) or worse with protein…

Improving Conditioning in Context-Aware Sequence to Sequence Models

2019-11-21 · Xinyi Wang, Jason Weston, Michael Auli, Yacine Jernite

Neural sequence to sequence models are well established for applications which can be cast as mapping a single input sequence into a single output sequence. In this work, we focus on cases where generation is conditioned…

abstractive question answeringData AugmentationOpen-Domain Question AnsweringQuestion Answering+1

Design in the Dark: Learning Deep Generative Models for De Novo Protein Design

2021-09-29 · Lewis Moffat, Shaun M. Kandathil, David T. Jones

The design of novel protein sequences is providing paths towards the development of novel therapeutics and materials. Generative modelling approaches to design are emerging and to date have required conditioning on 3D p…

Protein Design

Do RNN States Encode Abstract Phonological Processes?

2021-04-01 · Miikka Silfverberg, Francis Tyers, Garrett Nicolai, Mans Hulden

Sequence-to-sequence models have delivered impressive results in word formation tasks such as morphological inflection, often learning to model subtle morphophonological details with limited training data. Despite the pe…

MemorizationMorphological Inflection