Image de couverture de livre

Analyzing the Importance of Blank for CTC-Based Knowledge Distillation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hilmes, Benedikt, Rossenbach, Nick, Schlüter, Ralf
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning 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

On the Effect of Purely Synthetic Training Data for Different Automatic Speech Recognition Architectures
par: Hilmes, Benedikt, et autres
Publié: (2024)

On the Problem of Text-To-Speech Model Selection for Synthetic Data Generation in Automatic Speech Recognition
par: Rossenbach, Nick, et autres
Publié: (2024)

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

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

CTC Blank Triggered Dynamic Layer-Skipping for Efficient CTC-based Speech Recognition
par: Hou, Junfeng, et autres
Publié: (2024)

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

CR-CTC: Consistency regularization on CTC for improved speech recognition
par: Yao, Zengwei, et autres
Publié: (2024)

Guiding Frame-Level CTC Alignments Using Self-knowledge Distillation
par: Kim, Eungbeom, et autres
Publié: (2024)

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

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

CJST: CTC Compressor based Joint Speech and Text Training for Decoder-Only ASR
par: Zhou, Wei, et autres
Publié: (2024)

Delayed-KD: Delayed Knowledge Distillation based CTC for Low-Latency Streaming ASR
par: Li, Longhao, et autres
Publié: (2025)

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

FLToP CTC: Frame-Level Token Pruning via Relative Threshold for Efficient and Memory-Saving Decoding on Diverse Platforms
par: Shree, Atul, et autres
Publié: (2025)

Creating a Good Teacher for Knowledge Distillation in Acoustic Scene Classification
par: Morocutti, Tobias, et autres
Publié: (2025)

Knowledge Distillation for Speech Denoising by Latent Representation Alignment with Cosine Distance
par: Luong, Diep, et autres
Publié: (2025)

Music Boomerang: Reusing Diffusion Models for Data Augmentation and Audio Manipulation
par: Fichtinger, Alexander, et autres
Publié: (2025)

Beat this! Accurate beat tracking without DBN postprocessing
par: Foscarin, Francesco, et autres
Publié: (2024)

The Rarity of Musical Audio Signals Within the Space of Possible Audio Generation
par: Collins, Nick
Publié: (2024)

Exploring System Adaptations For Minimum Latency Real-Time Piano Transcription
par: Hu, Patricia, et autres
Publié: (2025)

kNN-CTC: Enhancing ASR via Retrieval of CTC Pseudo Labels
par: Zhou, Jiaming, et autres
Publié: (2023)

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

FlexCTC: GPU-powered CTC Beam Decoding With Advanced Contextual Abilities
par: Grigoryan, Lilit, et autres
Publié: (2025)

Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework
par: Segev, Eliya, et autres
Publié: (2023)

Adversarial Speaker Distillation for Countermeasure Model on Automatic Speaker Verification
par: Liao, Yen-Lun, et autres
Publié: (2022)

Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter
par: Andrusenko, Andrei, et autres
Publié: (2024)

Enhancing Code-Switching ASR Leveraging Non-Peaky CTC Loss and Deep Language Posterior Injection
par: Yang, Tzu-Ting, et autres
Publié: (2024)

ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation
par: Bai, Yatong, et autres
Publié: (2023)

Knowledge boosting during low-latency inference
par: Srinivas, Vidya, et autres
Publié: (2024)

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

SegAug: CTC-Aligned Segmented Augmentation For Robust RNN-Transducer Based Speech Recognition
par: Le, Khanh, et autres
Publié: (2025)

NTC-KWS: Noise-aware CTC for Robust Keyword Spotting
par: Xi, Yu, et autres
Publié: (2024)

DeCoR: Defy Knowledge Forgetting by Predicting Earlier Audio Codes
par: Jiang, Xilin, et autres
Publié: (2023)

Cross-Domain Knowledge Transfer for Underwater Acoustic Classification Using Pre-trained Models
par: Mohammadi, Amirmohammad, et autres
Publié: (2024)

Error Analysis in a Modular Meeting Transcription System
par: Vieting, Peter, et autres
Publié: (2025)

Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription
par: Vieting, Peter, et autres
Publié: (2023)

Score-Based Training for Energy-Based TTS Models
par: Sun, Wanli, et autres
Publié: (2025)

Decoder-only Architecture for Speech Recognition with CTC Prompts and Text Data Augmentation
par: Tsunoo, Emiru, et autres
Publié: (2023)

Diffusion-Based Speech Enhancement in Matched and Mismatched Conditions Using a Heun-Based Sampler
par: Gonzalez, Philippe, et autres
Publié: (2023)

Classification of Short Segment Pediatric Heart Sounds Based on a Transformer-Based Convolutional Neural Network
par: Hassanuzzaman, Md, et autres
Publié: (2024)