Cover Image

Sequence-Level Unsupervised Training in Speech Recognition: A Theoretical Study

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Zijian, Barkoczi, Jörg, Schlüter, Ralf, Ney, Hermann
Format:	Preprint
Published:	2026
Subjects:	Sound Machine Learning Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

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

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

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

Unified Learnable 2D Convolutional Feature Extraction for ASR
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)

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)

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

Accent Conversion in Text-To-Speech Using Multi-Level VAE and Adversarial Training
by: Melechovsky, Jan, et al.
Published: (2024)

Unsupervised Rhythm and Voice Conversion to Improve ASR on Dysarthric Speech
by: Hajal, Karl El, et al.
Published: (2025)

Unsupervised Rhythm and Voice Conversion of Dysarthric to Healthy Speech for ASR
by: Hajal, Karl El, et al.
Published: (2025)

Posterior Transition Modeling for Unsupervised Diffusion-Based Speech Enhancement
by: Sadeghi, Mostafa, et al.
Published: (2025)

Multi-blank Transducers for Speech Recognition
by: Xu, Hainan, et al.
Published: (2022)

VoxGenesis: Unsupervised Discovery of Latent Speaker Manifold for Speech Synthesis
by: Lin, Weiwei, et al.
Published: (2024)

Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis
by: Jiang, Xilin, et al.
Published: (2024)

Test-Time Adaptation for Speech Emotion Recognition
by: Dong, Jiaheng, et al.
Published: (2026)

Drax: Speech Recognition with Discrete Flow Matching
by: Navon, Aviv, et al.
Published: (2025)

Adapting WavLM for Speech Emotion Recognition
by: Diatlova, Daria, et al.
Published: (2024)

Keyword-Guided Adaptation of Automatic Speech Recognition
by: Shamsian, Aviv, et al.
Published: (2024)

Multimodal Attention Merging for Improved Speech Recognition and Audio Event Classification
by: Sundar, Anirudh S., et al.
Published: (2023)

Test-Time Training for Speech Enhancement
by: Behera, Avishkar, et al.
Published: (2025)

Non-intrusive Speech Quality Assessment with Diffusion Models Trained on Clean Speech
by: de Oliveira, Danilo, et al.
Published: (2024)

TRNet: Two-level Refinement Network leveraging Speech Enhancement for Noise Robust Speech Emotion Recognition
by: Chen, Chengxin, et al.
Published: (2024)

Enhancing Speech Emotion Recognition Through Differentiable Architecture Search
by: Rajapakshe, Thejan, et al.
Published: (2023)

Parameter Efficient Finetuning for Speech Emotion Recognition and Domain Adaptation
by: Lashkarashvili, Nineli, et al.
Published: (2024)

A Layer-Anchoring Strategy for Enhancing Cross-Lingual Speech Emotion Recognition
by: Upadhyay, Shreya G., et al.
Published: (2024)

Transcription-Free Fine-Tuning of Speech Separation Models for Noisy and Reverberant Multi-Speaker Automatic Speech Recognition
by: Ravenscroft, William, et al.
Published: (2024)

Representation Learning with Parameterised Quantum Circuits for Advancing Speech Emotion Recognition
by: Rajapakshe, Thejan, et al.
Published: (2025)

Adapting Automatic Speech Recognition for Accented Air Traffic Control Communications
by: Wee, Marcus Yu Zhe, et al.
Published: (2025)

Revealing Emotional Clusters in Speaker Embeddings: A Contrastive Learning Strategy for Speech Emotion Recognition
by: Ulgen, Ismail Rasim, et al.
Published: (2024)

Enhancing Speech Emotion Recognition using Dynamic Spectral Features and Kalman Smoothing
by: Hizabri, Marouane El, et al.
Published: (2026)

Edge-ASR: Towards Low-Bit Quantization of Automatic Speech Recognition Models
by: Feng, Chen, et al.
Published: (2025)

Domain Adapting Deep Reinforcement Learning for Real-world Speech Emotion Recognition
by: Rajapakshe, Thejan, et al.
Published: (2022)

Gradient Norm-based Fine-Tuning for Backdoor Defense in Automatic Speech Recognition
by: Zhou, Nanjun, et al.
Published: (2025)

Mouth Articulation-Based Anchoring for Improved Cross-Corpus Speech Emotion Recognition
by: Upadhyay, Shreya G., et al.
Published: (2024)

CORN: Co-Trained Full- And No-Reference Speech Quality Assessment
by: Manocha, Pranay, et al.
Published: (2023)

Behind the Scenes: Mechanistic Interpretability of LoRA-adapted Whisper for Speech Emotion Recognition
by: Ma, Yujian, et al.
Published: (2025)