Multilingual TASU: Extending Text-Only Alignment to Multilingual Speech Recognition via Simulated CTC Posteriors
eess.AS
Submitted: 2026-10-31
Updated: 2026-10-31
Comments: Accepted at NCMMSC 2026, to appear in Springer CCIS
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- On The Landscape of Spoken Language Models: A Comprehensive Survey
- Qwen2-Audio Technical Report
- LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriors
- An Embarrassingly Simple Approach for LLM with Strong ASR Capacity
- Qwen2.5-Omni Technical Report
- Kimi-Audio Technical Report
- TASU: Text-Only Alignment for Speech Understanding
- TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs
- WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit
- Qwen2.5 Technical Report
Related papers
- WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling
- From perception to production: how acoustic invariance facilitates articulatory learning in a self-supervised vocal imitation model
- Read What You Hear: Reference-Free Hypotheses Evaluation with Acoustic Discrepancy
- pyFDN: A Python Toolbox for Feedback Delay Network Design, Analysis, and Optimization
- GigaSpeechBench: A Real-World Multilingual Speech-to-Text Benchmark
- DM-ASR: Diarization-aware Multi-speaker ASR with Unified Offline and Online Decoding with Large Language Models