Image de couverture de livre

Outlier Reduction with Gated Attention for Improved Post-training Quantization in Large Sequence-to-sequence Speech Foundation Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wagner, Dominik, Baumann, Ilja, Riedhammer, Korbinian, Bocklet, Tobias
Format:	Preprint
Publié:	2024
Sujets:	Sound Audio and Speech Processing
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Personalized Fine-Tuning with Controllable Synthetic Speech from LLM-Generated Transcripts for Dysarthric Speech Recognition
par: Wagner, Dominik, et autres
Publié: (2025)

Large Language Models for Dysfluency Detection in Stuttered Speech
par: Wagner, Dominik, et autres
Publié: (2024)

Vocoder-Free Non-Parallel Conversion of Whispered Speech With Masked Cycle-Consistent Generative Adversarial Networks
par: Wagner, Dominik, et autres
Publié: (2023)

Adapter-Based Multi-Agent AVSR Extension for Pre-Trained ASR Models
par: Simic, Christopher, et autres
Publié: (2025)

Detecting Dysfluencies in Stuttering Therapy Using wav2vec 2.0
par: Bayerl, Sebastian P., et autres
Publié: (2022)

Infusing Acoustic Pause Context into Text-Based Dementia Assessment
par: Braun, Franziska, et autres
Publié: (2024)

Optimized Self-supervised Training with BEST-RQ for Speech Recognition
par: Baumann, Ilja, et autres
Publié: (2025)

A Survey of Music Generation in the Context of Interaction
par: Agchar, Ismael, et autres
Publié: (2024)

FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer
par: Wang, Haoxu, et autres
Publié: (2025)

The PARLO Dementia Corpus: A German Multi-Center Resource for Alzheimer's Disease
par: Braun, Franziska, et autres
Publié: (2026)

A Perception-Based L2 Speech Intelligibility Indicator: Leveraging a Rater's Shadowing and Sequence-to-sequence Voice Conversion
par: Geng, Haopeng, et autres
Publié: (2025)

Post-Training Quantization for Audio Diffusion Transformers
par: Khandelwal, Tanmay, et autres
Publié: (2025)

Pitfalls and Limits in Automatic Dementia Assessment
par: Braun, Franziska, et autres
Publié: (2025)

Improving Speech Emotion Recognition Through Cross Modal Attention Alignment and Balanced Stacking Model
par: Ueda, Lucas, et autres
Publié: (2025)

Improving Streaming Speech Recognition With Time-Shifted Contextual Attention And Dynamic Right Context Masking
par: Le, Khanh, et autres
Publié: (2025)

Addressing Index Collapse of Large-Codebook Speech Tokenizer with Dual-Decoding Product-Quantized Variational Auto-Encoder
par: Guo, Haohan, et autres
Publié: (2024)

USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models
par: Ding, Shaojin, et autres
Publié: (2023)

Vector Quantized Diffusion Model Based Speech Bandwidth Extension
par: Fang, Yuan, et autres
Publié: (2024)

Effective and Efficient Mixed Precision Quantization of Speech Foundation Models
par: Xu, Haoning, et autres
Publié: (2025)

Cross-Talk Speech Reduction, by Separation, for Separation
par: Wang, Zhong-Qiu, et autres
Publié: (2026)

Using Speech Foundational Models in Loss Functions for Hearing Aid Speech Enhancement
par: Sutherland, Robert, et autres
Publié: (2024)

Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration
par: Ku, Pin-Jui, et autres
Publié: (2024)

On the Difficulty of Token-Level Modeling of Dysfluency and Fluency Shaping Artifacts
par: Gulzar, Kashaf, et autres
Publié: (2025)

SAC: Neural Speech Codec with Semantic-Acoustic Dual-Stream Quantization
par: Chen, Wenxi, et autres
Publié: (2025)

Mamba in Speech: Towards an Alternative to Self-Attention
par: Zhang, Xiangyu, et autres
Publié: (2024)

Analysing the Masked predictive coding training criterion for pre-training a Speech Representation Model
par: Yadav, Hemant, et autres
Publié: (2023)

Prosody Labeling with Phoneme-BERT and Speech Foundation Models
par: Koriyama, Tomoki
Publié: (2025)

ESC: Efficient Speech Coding with Cross-Scale Residual Vector Quantized Transformers
par: Gu, Yuzhe, et autres
Publié: (2024)

Vox-Profile: A Speech Foundation Model Benchmark for Characterizing Diverse Speaker and Speech Traits
par: Feng, Tiantian, et autres
Publié: (2025)

Speaker Disentanglement of Speech Pre-trained Model Based on Interpretability
par: Zhu, Xiaoxu, et autres
Publié: (2025)

Chunk Based Speech Pre-training with High Resolution Finite Scalar Quantization
par: Tang, Yun, et autres
Publié: (2025)

Attention-Guided Adaptation for Code-Switching Speech Recognition
par: Aditya, Bobbi, et autres
Publié: (2023)

Reverse Attention for Lightweight Speech Enhancement on Edge Devices
par: Ojha, Shuubham, et autres
Publié: (2025)

Attention-Based Beamformer For Multi-Channel Speech Enhancement
par: Bai, Jinglin, et autres
Publié: (2024)

Self-Supervised Speech Quality Assessment (S3QA): Leveraging Speech Foundation Models for a Scalable Speech Quality Metric
par: Ogg, Mattson, et autres
Publié: (2025)

Neural Speech Coding for Real-time Communications using Constant Bitrate Scalar Quantization
par: Brendel, Andreas, et autres
Publié: (2024)

Causal Speech Enhancement with Predicting Semantics based on Quantized Self-supervised Learning Features
par: Tsunoo, Emiru, et autres
Publié: (2024)

FireRedTTS: A Foundation Text-To-Speech Framework for Industry-Level Generative Speech Applications
par: Guo, Hao-Han, et autres
Publié: (2024)

Attention-weighted Centered Kernel Alignment for Knowledge Distillation in Large Audio-Language Models Applied to Speech Emotion Recognition
par: Yang, Qingran, et autres
Publié: (2026)

Target Speech Extraction with Pre-trained Self-supervised Learning Models
par: Peng, Junyi, et autres
Publié: (2024)