Cover Image

Unified Learnable 2D Convolutional Feature Extraction for ASR

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Vieting, Peter, Hilmes, Benedikt, Schlüter, Ralf, Ney, Hermann
Format:	Preprint
Published:	2025
Subjects:	Audio and Speech Processing Computation and Language Machine Learning Sound
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Regularizing Learnable Feature Extraction for Automatic Speech Recognition
by: Vieting, Peter, et al.
Published: (2025)

On the Effect of Purely Synthetic Training Data for Different Automatic Speech Recognition Architectures
by: Hilmes, Benedikt, et al.
Published: (2024)

Analyzing the Importance of Blank for CTC-Based Knowledge Distillation
by: Hilmes, Benedikt, et al.
Published: (2025)

On the Relation between Internal Language Model and Sequence Discriminative Training for Neural Transducers
by: Yang, Zijian, et al.
Published: (2023)

Label-Context-Dependent Internal Language Model Estimation for CTC
by: Yang, Zijian, et al.
Published: (2025)

Error Analysis in a Modular Meeting Transcription System
by: Vieting, Peter, et al.
Published: (2025)

Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription
by: Vieting, Peter, et al.
Published: (2023)

Right Label Context in End-to-End Training of Time-Synchronous ASR Models
by: Raissi, Tina, et al.
Published: (2025)

Chunked Attention-based Encoder-Decoder Model for Streaming Speech Recognition
by: Zeineldeen, Mohammad, et al.
Published: (2023)

Sequence-Level Unsupervised Training in Speech Recognition: A Theoretical Study
by: Yang, Zijian, et al.
Published: (2026)

The Conformer Encoder May Reverse the Time Dimension
by: Schmitt, Robin, et al.
Published: (2024)

Investigating the Effect of Label Topology and Training Criterion on ASR Performance and Alignment Quality
by: Raissi, Tina, et al.
Published: (2024)

On the Problem of Text-To-Speech Model Selection for Synthetic Data Generation in Automatic Speech Recognition
by: Rossenbach, Nick, et al.
Published: (2024)

Beyond Transcription: Mechanistic Interpretability in ASR
by: Glazer, Neta, et al.
Published: (2025)

Anatomy of Industrial Scale Multilingual ASR
by: Ramirez, Francis McCann, et al.
Published: (2024)

SALSA: Speedy ASR-LLM Synchronous Aggregation
by: Mittal, Ashish, et al.
Published: (2024)

Revisiting ASR Error Correction with Specialized Models
by: Gu, Zijin, et al.
Published: (2024)

Unsupervised ASR via Cross-Lingual Pseudo-Labeling
by: Likhomanenko, Tatiana, et al.
Published: (2023)

Federated Learning of Large ASR Models in the Real World
by: Xiao, Yonghui, et al.
Published: (2024)

Exploring Pathological Speech Quality Assessment with ASR-Powered Wav2Vec2 in Data-Scarce Context
by: Nguyen, Tuan, et al.
Published: (2024)

Cross-utterance ASR Rescoring with Graph-based Label Propagation
by: Tankasala, Srinath, et al.
Published: (2023)

Efficient Adapter Finetuning for Tail Languages in Streaming Multilingual ASR
by: Bai, Junwen, et al.
Published: (2024)

Conversational Rubert for Detecting Competitive Interruptions in ASR-Transcribed Dialogues
by: Galimzianov, Dmitrii, et al.
Published: (2024)

Transformer-based Model for ASR N-Best Rescoring and Rewriting
by: Kang, Iwen E., et al.
Published: (2024)

Contextualization of ASR with LLM using phonetic retrieval-based augmentation
by: Lei, Zhihong, et al.
Published: (2024)

Dysarthria Normalization via Local Lie Group Transformations for Robust ASR
by: Osipov, Mikhail
Published: (2025)

Conformer-1: Robust ASR via Large-Scale Semisupervised Bootstrapping
by: Zhang, Kevin, et al.
Published: (2024)

Text-only adaptation in LLM-based ASR through text denoising
by: Carofilis, Andrés, et al.
Published: (2026)

OLMoASR: Open Models and Data for Training Robust Speech Recognition Models
by: Ngo, Huong, et al.
Published: (2025)

Learn and Don't Forget: Adding a New Language to ASR Foundation Models
by: Qian, Mengjie, et al.
Published: (2024)

Enhanced ASR Robustness to Packet Loss with a Front-End Adaptation Network
by: Dissen, Yehoshua, et al.
Published: (2024)

Medical Spoken Named Entity Recognition
by: Le-Duc, Khai, et al.
Published: (2024)

In-Sync: Adaptation of Speech Aware Large Language Models for ASR with Word Level Timestamp Predictions
by: Fan, Xulin, et al.
Published: (2026)

A light-weight and efficient punctuation and word casing prediction model for on-device streaming ASR
by: You, Jian, et al.
Published: (2024)

XLS-R Deep Learning Model for Multilingual ASR on Low- Resource Languages: Indonesian, Javanese, and Sundanese
by: Arisaputra, Panji, et al.
Published: (2024)

Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator
by: Bataev, Vladimir, et al.
Published: (2023)

Enhancing Code-Switching ASR Leveraging Non-Peaky CTC Loss and Deep Language Posterior Injection
by: Yang, Tzu-Ting, et al.
Published: (2024)

Revisiting Acoustic Features for Robust ASR
by: Shah, Muhammad A., et al.
Published: (2024)

Evaluating Standard and Dialectal Frisian ASR: Multilingual Fine-tuning and Language Identification for Improved Low-resource Performance
by: Amooie, Reihaneh, et al.
Published: (2025)

Benchmarking Akan ASR Models Across Domain-Specific Datasets: A Comparative Evaluation of Performance, Scalability, and Adaptability
by: Mensah, Mark Atta, et al.
Published: (2025)