Pith. sign in

REVIEW 2 cited by

Comparing Discrete and Continuous Space LLMs 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 2409.00800 v1 pith:SQCIQHCM submitted 2024-09-01 cs.CL

classification cs.CL
keywords continuousspeechdiscretelanguagellmsmodelrecognitionrepresentations
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper investigates discrete and continuous speech representations in Large Language Model (LLM)-based Automatic Speech Recognition (ASR), organizing them by feature continuity and training approach into four categories: supervised and unsupervised for both discrete and continuous types. We further classify LLMs based on their input and autoregressive feedback into continuous and discrete-space models. Using specialized encoders and comparative analysis with a Joint-Training-From-Scratch Language Model (JTFS LM) and pre-trained LLaMA2-7b, we provide a detailed examination of their effectiveness. Our work marks the first extensive comparison of speech representations in LLM-based ASR and explores various modeling techniques. We present an open-sourced achievement of a state-of-the-art Word Error Rate (WER) of 1.69\% on LibriSpeech using a HuBERT encoder, offering valuable insights for advancing ASR and natural language processing (NLP) research.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. HASRD: Hierarchical Acoustic and Semantic Representation Disentanglement

    eess.AS 2025-06 conditional novelty 5.0 of 10

    HASRD factorizes SSL speech representations into a first semantic codebook and residual acoustic codebooks, reporting improved ASR and reconstruction at 3.1 kbps versus SpeechTokenizer's 6.0 kbps.

  2. Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs

    cs.CL 2025-08 unverdicted novelty 4.0 of 10

    Under matched settings, continuous SSL speech features generally outperform discrete tokens on six spoken language understanding tasks in SpeechLLMs.

Pith tools