Scaling Spoken Language Models with Syllabic Speech Tokenization

• URL: http://arxiv.org/abs/2509.26634v1
• Date: Tue, 30 Sep 2025 17:59:09 GMT
• Title: Scaling Spoken Language Models with Syllabic Speech Tokenization
• Authors: Nicholas Lee, Cheol Jun Cho, Alan W Black, Gopala K. Anumanchipalli,
• Abstract summary: Spoken language models (SLMs) typically discretize speech into high-frame-rate tokens extracted from SSL speech models.<n>Recent SSL work introduces acoustic tokenization of speech at the syllable level.<n>Syllabic tokens can match or surpass the previous high-frame rate tokens while significantly cutting training and inference costs.
• Score: 17.835120807367677
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spoken language models (SLMs) typically discretize speech into high-frame-rate tokens extracted from SSL speech models. As the most successful LMs are based on the Transformer architecture, processing these long token streams with self-attention is expensive, as attention scales quadratically with sequence length. A recent SSL work introduces acoustic tokenization of speech at the syllable level, which is more interpretable and potentially more scalable with significant compression in token lengths (4-5 Hz). Yet, their value for spoken language modeling is not yet fully explored. We present the first systematic study of syllabic tokenization for spoken language modeling, evaluating models on a suite of SLU benchmarks while varying training data scale. Syllabic tokens can match or surpass the previous high-frame rate tokens while significantly cutting training and inference costs, achieving more than a 2x reduction in training time and a 5x reduction in FLOPs. Our findings highlight syllable-level language modeling as a promising path to efficient long-context spoken language models.

Related papers

• ProsodyLM: Uncovering the Emerging Prosody Processing Capabilities in Speech Language Models [70.56468982313834]
  We propose ProsodyLM, which introduces a simple tokenization scheme amenable to learning prosody.<n>We find that ProsodyLM can learn surprisingly diverse emerging prosody processing capabilities through pre-training alone.
  arXiv  Detail & Related papers  (2025-07-27T00:59:01Z)
• Long-Form Speech Generation with Spoken Language Models [64.29591880693468]
  Textless spoken language models struggle to generate plausible speech past tens of seconds.<n>We derive SpeechSSM, the first speech language model family to learn from and sample long-form spoken audio.<n>SpeechSSMs leverage recent advances in linear-time sequence modeling to greatly surpass current Transformer spoken LMs in coherence and efficiency.
  arXiv  Detail & Related papers  (2024-12-24T18:56:46Z)
• CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models [74.80386066714229]
  We present an improved streaming speech synthesis model, CosyVoice 2.<n>Specifically, we introduce finite-scalar quantization to improve codebook utilization of speech tokens.<n>We develop a chunk-aware causal flow matching model to support various synthesis scenarios.
  arXiv  Detail & Related papers  (2024-12-13T12:59:39Z)
• Sylber: Syllabic Embedding Representation of Speech from Raw Audio [25.703703711031178]
  We propose a new model, Sylber, that produces speech representations with clean and robust syllabic structure.<n>Specifically, we propose a self-supervised learning framework that bootstraps syllabic embeddings by distilling from its own initial unsupervised syllabic segmentation.<n>This results in a highly structured representation of speech features, offering three key benefits: 1) a fast, linear-time syllable segmentation algorithm, 2) efficient syllabic tokenization with an average of 4.27 tokens per second, and 3) novel phonological units suited for efficient spoken language modeling.
  arXiv  Detail & Related papers  (2024-10-09T17:59:04Z)
• SyllableLM: Learning Coarse Semantic Units for Speech Language Models [21.762112843104028]
  We introduce a controllable self-supervised technique to merge speech representations into coarser syllable-like units. Our method produces controllable-rate semantic units at as low as 5Hz and 60bps and SotA inc segmentation and clustering. SyllableLM achieves significant improvements in efficiency with a 30x reduction in training compute and a 4x wall-clock inference speedup.
  arXiv  Detail & Related papers  (2024-10-05T04:29:55Z)
• Scaling Properties of Speech Language Models [4.0142527158949415]
  Speech Language Models (SLMs) aim to learn language from raw audio, without textual resources. We estimate the scale at which our current methods will yield a SLM with the English proficiency of text-based Large Language Models (LLMs)
  arXiv  Detail & Related papers  (2024-03-31T13:30:12Z)
• M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to Image Retrieval [56.49878599920353]
  This work investigates the use of large-scale, English-only pre-trained models (CLIP and HuBERT) for multilingual image-speech retrieval. For non-English image-speech retrieval, we outperform the current state-of-the-art performance by a wide margin both when training separate models for each language, and with a single model which processes speech in all three languages.
  arXiv  Detail & Related papers  (2022-11-02T14:54:45Z)
• Evidence of Vocal Tract Articulation in Self-Supervised Learning of Speech [15.975756437343742]
  Recent self-supervised learning (SSL) models have proven to learn rich representations of speech. We conduct a comprehensive analysis to link speech representations to articulatory trajectories measured by electromagnetic articulography (EMA) Our findings suggest that SSL models learn to align closely with continuous articulations, and provide a novel insight into speech SSL.
  arXiv  Detail & Related papers  (2022-10-21T04:24:29Z)
• Automatic Pronunciation Assessment using Self-Supervised Speech Representation Learning [13.391307807956673]
  We propose a novel automatic pronunciation assessment method based on self-supervised learning (SSL) models. First, the proposed method fine-tunes the pre-trained SSL models with connectionist temporal classification to adapt the English pronunciation of English-as-a-second-language learners. We show that the proposed SSL model-based methods outperform the baselines, in terms of the Pearson correlation coefficient, on datasets of Korean ESL learner children and Speechocean762.
  arXiv  Detail & Related papers  (2022-04-08T06:13:55Z)
• Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units [56.52704348773307]
  We propose a novel LSTM-based generative speech LM based on linguistic units including syllables and phonemes. With a limited dataset, orders of magnitude smaller than that required by contemporary generative models, our model closely approximates babbling speech. We show the effect of training with auxiliary text LMs, multitask learning objectives, and auxiliary articulatory features.
  arXiv  Detail & Related papers  (2021-10-31T22:48:30Z)
• Continual-wav2vec2: an Application of Continual Learning for Self-Supervised Automatic Speech Recognition [0.23872611575805824]
  We present a method for continual learning of speech representations for multiple languages using self-supervised learning (SSL) Wav2vec models perform SSL on raw audio in a pretraining phase and then finetune on a small fraction of annotated data. We use ideas from continual learning to transfer knowledge from a previous task to speed up pretraining a new language task.
  arXiv  Detail & Related papers  (2021-07-26T10:39:03Z)
• SPLAT: Speech-Language Joint Pre-Training for Spoken Language Understanding [61.02342238771685]
  Spoken language understanding requires a model to analyze input acoustic signal to understand its linguistic content and make predictions. Various pre-training methods have been proposed to learn rich representations from large-scale unannotated speech and text. We propose a novel semi-supervised learning framework, SPLAT, to jointly pre-train the speech and language modules.
  arXiv  Detail & Related papers  (2020-10-05T19:29:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.