Image de couverture de livre

Dynamic Acoustic Model Architecture Optimization in Training for ASR

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xu, Jingjing, Yang, Zijian, Zeyer, Albert, Beck, Eugen, Schlueter, Ralf, Ney, Hermann
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Efficient Supernet Training with Orthogonal Softmax for Scalable ASR Model Compression
par: Xu, Jingjing, et autres
Publié: (2025)

Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition
par: Xu, Jingjing, et autres
Publié: (2024)

Text-Utilization for Encoder-dominated Speech Recognition Models
par: Zeyer, Albert, et autres
Publié: (2026)

Diffusion Language Models for Speech Recognition
par: Naveriani, Davyd, et autres
Publié: (2026)

On the Relation between Internal Language Model and Sequence Discriminative Training for Neural Transducers
par: Yang, Zijian, et autres
Publié: (2023)

Reproducing and Dissecting Denoising Language Models for Speech Recognition
par: Koch, Dorian, et autres
Publié: (2025)

Unified Learnable 2D Convolutional Feature Extraction for ASR
par: Vieting, Peter, et autres
Publié: (2025)

Label-Context-Dependent Internal Language Model Estimation for CTC
par: Yang, Zijian, et autres
Publié: (2025)

A Comparative Analysis on ASR System Combination for Attention, CTC, Factored Hybrid, and Transducer Models
par: Bayoumi, Noureldin, et autres
Publié: (2025)

Chunked Attention-based Encoder-Decoder Model for Streaming Speech Recognition
par: Zeineldeen, Mohammad, et autres
Publié: (2023)

Right Label Context in End-to-End Training of Time-Synchronous ASR Models
par: Raissi, Tina, et autres
Publié: (2025)

LLMs and Speech: Integration vs. Combination
par: Schmitt, Robin, et autres
Publié: (2026)

The Conformer Encoder May Reverse the Time Dimension
par: Schmitt, Robin, et autres
Publié: (2024)

AppTek Call-Center Dialogues: A Multi-Accent Long-Form Benchmark for English ASR
par: Beck, Eugen, et autres
Publié: (2026)

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation
par: Liu, Dancheng, et autres
Publié: (2025)

Boosting Hybrid Autoregressive Transducer-based ASR with Internal Acoustic Model Training and Dual Blank Thresholding
par: Moriya, Takafumi, et autres
Publié: (2024)

Revisiting Acoustic Features for Robust ASR
par: Shah, Muhammad A., et autres
Publié: (2024)

Listen to the Context: Towards Faithful Large Language Models for Retrieval Augmented Generation on Climate Questions
par: Thulke, David, et autres
Publié: (2025)

Regularizing Learnable Feature Extraction for Automatic Speech Recognition
par: Vieting, Peter, et autres
Publié: (2025)

Sequence-Level Unsupervised Training in Speech Recognition: A Theoretical Study
par: Yang, Zijian, et autres
Publié: (2026)

The Limits of Data Scaling: Sub-token Utilization and Acoustic Saturation in Multilingual ASR
par: Liang, Siyu, et autres
Publié: (2025)

CALM: Joint Contextual Acoustic-Linguistic Modeling for Personalization of Multi-Speaker ASR
par: Shakeel, Muhammad, et autres
Publié: (2026)

MLMA: Towards Multilingual ASR With Mamba-based Architectures
par: Ali, Mohamed Nabih, et autres
Publié: (2025)

Investigating the Effect of Label Topology and Training Criterion on ASR Performance and Alignment Quality
par: Raissi, Tina, et autres
Publié: (2024)

Echoes of Phonetics: Unveiling Relevant Acoustic Cues for ASR via Feature Attribution
par: Fucci, Dennis, et autres
Publié: (2025)

New Insights into Optimal Alignment of Acoustic and Linguistic Representations for Knowledge Transfer in ASR
par: Lu, Xugang, et autres
Publié: (2025)

Uni-ASR: Unified LLM-Based Architecture for Non-Streaming and Streaming Automatic Speech Recognition
par: Xia, Yinfeng, et autres
Publié: (2026)

Prompting and Fine-Tuning of Small LLMs for Length-Controllable Telephone Call Summarization
par: Thulke, David, et autres
Publié: (2024)

Optimizing Speech Language Models for Acoustic Consistency
par: Rohanian, Morteza, et autres
Publié: (2025)

Functional Abstraction of Knowledge Recall in Large Language Models
par: Wang, Zijian, et autres
Publié: (2025)

Eliciting Chain-of-Thought in Base LLMs via Gradient-Based Representation Optimization
par: Wang, Zijian, et autres
Publié: (2025)

Vividh-ASR: A Complexity-Tiered Benchmark and Optimization Dynamics for Robust Indic Speech Recognition
par: Juvekar, Kush, et autres
Publié: (2026)

PromptASR for contextualized ASR with controllable style
par: Yang, Xiaoyu, et autres
Publié: (2023)

Towards interfacing large language models with ASR systems using confidence measures and prompting
par: Naderi, Maryam, et autres
Publié: (2024)

Classification Error Bound for Low Bayes Error Conditions in Machine Learning
par: Yang, Zijian, et autres
Publié: (2025)

Refined Statistical Bounds for Classification Error Mismatches with Constrained Bayes Error
par: Yang, Zijian, et autres
Publié: (2024)

OLMoASR: Open Models and Data for Training Robust Speech Recognition Models
par: Ngo, Huong, et autres
Publié: (2025)

Task Arithmetic with Support Languages for Low-Resource ASR
par: Rafkin, Emma, et autres
Publié: (2026)

FTFT: Efficient and Robust Fine-Tuning by Transferring Training Dynamics
par: Du, Yupei, et autres
Publié: (2023)

Locating and Extracting Relational Concepts in Large Language Models
par: Wang, Zijian, et autres
Publié: (2024)