REVIEW 2 cited by
Group Relative Policy Optimization for Speech Recognition
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Group Relative Policy Optimization for Speech Recognition
read the original abstract
Speech Recognition has seen a dramatic shift towards adopting Large Language Models (LLMs). This shift is partly driven by good scalability properties demonstrated by LLMs, ability to leverage large amounts of labelled, unlabelled speech and text data, streaming capabilities with auto-regressive framework and multi-tasking with instruction following characteristics of LLMs. However, simple next-token prediction objective, typically employed with LLMs, have certain limitations in performance and challenges with hallucinations. In this paper, we propose application of Group Relative Policy Optimization (GRPO) to enable reinforcement learning from human feedback for automatic speech recognition (ASR). We design simple rule based reward functions to guide the policy updates. We demonstrate significant improvements in word error rate (upto 18.4% relative), reduction in hallucinations, increased robustness on out-of-domain datasets and effectiveness in domain adaptation.
Forward citations
Cited by 2 Pith papers
-
Reinforcement Learning for Data-Efficient Code-Switched ASR
RLVR with CER and script-fidelity rewards matches full-data LoRA SFT for code-switched ASR using only 10% TTS data across 10 language pairs, with zero-shot transfer to human speech.
-
FSA-GRPO: Teaching Auditory LLMs to Use Few-shot Demonstrations
FSA-GRPO applies reinforcement learning with a few-shot-aware reward to auditory LLMs, improving few-shot performance on children's ASR, speech translation, and audio tasks when trained only on adult data.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.