Pith. sign in

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

arxiv 2509.01939 v1 pith:DMMJWUEW submitted 2025-09-02 eess.AS

Group Relative Policy Optimization for Speech Recognition

classification eess.AS
keywords llmsspeechpolicyrecognitionrelativegrouphallucinationslarge
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Reinforcement Learning for Data-Efficient Code-Switched ASR

    cs.CL 2026-07 conditional novelty 5.0

    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.

  2. FSA-GRPO: Teaching Auditory LLMs to Use Few-shot Demonstrations

    eess.AS 2026-05 unverdicted novelty 4.0

    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.