Cover Image

Text-only adaptation in LLM-based ASR through text denoising

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Carofilis, Andrés, Burdisso, Sergio, Villatoro-Tello, Esaú, Kumar, Shashi, Hacioglu, Kadri, Madikeri, Srikanth, Rangappa, Pradeep, E, Manjunath K, Motlicek, Petr, Venkatesan, Shankar, Stolcke, Andreas
Format:	Preprint
Published:	2026
Subjects:	Sound Computation and Language 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

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation
by: Kumar, Shashi, et al.
Published: (2025)

Reducing Prompt Sensitivity in LLM-based Speech Recognition Through Learnable Projection
by: Burdisso, Sergio, et al.
Published: (2026)

Better Semi-supervised Learning for Multi-domain ASR Through Incremental Retraining and Data Filtering
by: Carofilis, Andres, et al.
Published: (2025)

Efficient Data Selection for Domain Adaptation of ASR Using Pseudo-Labels and Multi-Stage Filtering
by: Rangappa, Pradeep, et al.
Published: (2025)

Performance evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forward
by: Kumar, Shashi, et al.
Published: (2024)

Unifying Global and Near-Context Biasing in a Single Trie Pass
by: Thorbecke, Iuliia, et al.
Published: (2024)

Distilling Conversations: Abstract Compression of Conversational Audio Context for LLM-based ASR
by: Kumar, Shashi, et al.
Published: (2026)

XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models
by: Kumar, Shashi, et al.
Published: (2024)

TokenVerse: Towards Unifying Speech and NLP Tasks via Transducer-based ASR
by: Kumar, Shashi, et al.
Published: (2024)

Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whisper
by: Thorbecke, Iuliia, et al.
Published: (2024)

Node-weighted Graph Convolutional Network for Depression Detection in Transcribed Clinical Interviews
by: Burdisso, Sergio, et al.
Published: (2023)

Closing the Speech-Text Gap with Limited Audio for Effective Domain Adaptation in LLM-Based ASR
by: Bañeras-Roux, Thibault, et al.
Published: (2026)

Better Pseudo-labeling with Multi-ASR Fusion and Error Correction by SpeechLLM
by: Prakash, Jeena, et al.
Published: (2025)

Effectiveness of Text, Acoustic, and Lattice-based representations in Spoken Language Understanding tasks
by: Villatoro-Tello, Esaú, et al.
Published: (2022)

Dialog2Flow: Pre-training Soft-Contrastive Action-Driven Sentence Embeddings for Automatic Dialog Flow Extraction
by: Burdisso, Sergio, et al.
Published: (2024)

Improving endpoint detection in end-to-end streaming ASR for conversational speech
by: C, Anandh, et al.
Published: (2025)

When Consistency Becomes Bias: Interviewer Effects in Semi-Structured Clinical Interviews
by: Watawana, Hasindri, et al.
Published: (2026)

Reliability Estimation of News Media Sources: Birds of a Feather Flock Together
by: Burdisso, Sergio, et al.
Published: (2024)

Mapping the Media Landscape: Predicting Factual Reporting and Political Bias Through Web Interactions
by: Sánchez-Cortés, Dairazalia, et al.
Published: (2024)

Unifying Streaming and Non-streaming Zipformer-based ASR
by: Sharma, Bidisha, et al.
Published: (2025)

Adaptive Multimodal Person Recognition: A Robust Framework for Handling Missing Modalities
by: Farhadipour, Aref, et al.
Published: (2025)

Doctor or Patient? Synergizing Diarization and ASR for Code-Switched Hinglish Medical Conditions Extraction
by: Baroudi, Séverin, et al.
Published: (2026)

A Differentiable Alignment Framework for Sequence-to-Sequence Modeling via Optimal Transport
by: Kaloga, Yacouba, et al.
Published: (2025)

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

SpeechLLMs for Large-scale Contextualized Zero-shot Slot Filling
by: Hacioglu, Kadri, et al.
Published: (2025)

Slot Filling as a Reasoning Task for SpeechLLMs
by: Hacioglu, Kadri, et al.
Published: (2025)

SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation
by: Burdisso, Sergio, et al.
Published: (2025)

TidyVoice: A Curated Multilingual Dataset for Speaker Verification Derived from Common Voice
by: Farhadipour, Aref, et al.
Published: (2026)

SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation
by: Burdisso, Sergio, et al.
Published: (2025)

DAIC-WOZ: On the Validity of Using the Therapist's prompts in Automatic Depression Detection from Clinical Interviews
by: Burdisso, Sergio, et al.
Published: (2024)

IDIAPers @ Causal News Corpus 2022: Efficient Causal Relation Identification Through a Prompt-based Few-shot Approach
by: Burdisso, Sergio, et al.
Published: (2022)

Learning When to Trust Which Teacher for Weakly Supervised ASR
by: Agrawal, Aakriti, et al.
Published: (2023)

Spoofing-Aware Speaker Verification via Wavelet Prompt Tuning and Multi-Model Ensembles
by: Farhadipour, Aref, et al.
Published: (2026)

Text adaptation for speaker verification with speaker-text factorized embeddings
by: Yang, Yexin, et al.
Published: (2025)

A Probabilistic Method for Ranking Refinementin Geographic Information Retrieval
by: Esaú Villatoro-Tello
Published: (2010)

CL-UZH submission to the NIST SRE 2024 Speaker Recognition Evaluation
by: Farhadipour, Aref, et al.
Published: (2025)

Improving fairness in speaker verification via Group-adapted Fusion Network
by: Shen, Hua, et al.
Published: (2022)

Loss Masking Is Not Needed in Decoder-only Transformer for Discrete-token-based ASR
by: Chen, Qian, et al.
Published: (2023)

SOA: Reducing Domain Mismatch in SSL Pipeline by Speech Only Adaptation for Low Resource ASR
by: Shankar, Natarajan Balaji, et al.
Published: (2024)

CHSER: A Dataset and Case Study on Generative Speech Error Correction for Child ASR
by: Shankar, Natarajan Balaji, et al.
Published: (2025)