Pith. sign in

REVIEW 3 cited by

Efficient Streaming LLM 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 2410.03752 v1 pith:CDIPYR6R submitted 2024-10-02 cs.SD cs.AIcs.CLeess.AS

classification cs.SDcs.AIcs.CLeess.AS
keywords audiorecognitionspeechstreamingtrainingattentionchunkchunks
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent works have shown that prompting large language models with audio encodings can unlock speech recognition capabilities. However, existing techniques do not scale efficiently, especially while handling long form streaming audio inputs -- not only do they extrapolate poorly beyond the audio length seen during training, but they are also computationally inefficient due to the quadratic cost of attention. In this work, we introduce SpeechLLM-XL, a linear scaling decoder-only model for streaming speech recognition. We process audios in configurable chunks using limited attention window for reduced computation, and the text tokens for each audio chunk are generated auto-regressively until an EOS is predicted. During training, the transcript is segmented into chunks, using a CTC forced alignment estimated from encoder output. SpeechLLM-XL with 1.28 seconds chunk size achieves 2.7%/6.7% WER on LibriSpeech test clean/other, and it shows no quality degradation on long form utterances 10x longer than the training utterances.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Evaluation of LLMs in Speech is Often Flawed: Test Set Contamination in Large Language Models for Speech Recognition

    eess.AS 2025-05 conditional novelty 7.0 of 10

    LibriSpeech and Common Voice evaluation sentences leak into the Pile, and controlled LLM pretraining experiments show that contamination biases output probabilities even when error rates barely change.

  2. SimulS2ST-Omni: Data-Efficient Streaming Speech-to-Speech Translation via Explicit Trajectory Supervision

    cs.SD 2026-07 conditional novelty 6.0 of 10

    A joint text-code trajectory supervision recipe lets a two-stream speech LM achieve competitive long-form streaming S2ST with ~2k hours of paired speech.

  3. MFLA: Monotonic Finite Look-ahead Attention for Streaming Speech Recognition

    cs.CL 2025-06 conditional novelty 6.0 of 10

    MFLA adds finite look-ahead attention plus a CIF-based token counter to Whisper, enabling streaming recognition with a wait-k latency-quality trade-off.

Pith tools