PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization

• URL: http://arxiv.org/abs/2605.06582v1
• Date: Thu, 07 May 2026 17:11:22 GMT
• Title: PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization
• Abstract summary: PairAlign is a framework for compact audio tokenization through sequence-level self-alignment.<n>It learns compact, non-degenerate sequences with broad vocabulary usage.<n>It preserves edit-distance search while reducing archive token count by 55%.
• Score: 8.126475706520063
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many operations on sensory data -- comparison, memory, retrieval, and reasoning -- are naturally expressed over discrete symbolic structures. In language this interface is given by tokens; in audio, it must be learned. Existing audio tokenizers rely on quantization, clustering, or codec reconstruction, assigning tokens locally, so sequence consistency, compactness, length control, termination, and edit similarity are rarely optimized directly. We introduce PairAlign, a framework for compact audio tokenization through sequence-level self-alignment. PairAlign treats tokenization as conditional sequence generation: an encoder maps speech to a continuous condition, and an autoregressive decoder generates tokens from BOS, learning token identity, order, length, and EOS placement. Given two content-preserving views, each view's sequence is trained to be likely under the other's representation, while unrelated examples provide competing sequences. This gives a scalable surrogate for edit-distance preservation while discouraging many-to-one collapse. PairAlign starts from VQ-style tokenization and refines it with EMA-teacher targets, cross-paired teacher forcing, prefix corruption, likelihood contrast, and length control. On 3-second speech, PairAlign learns compact, non-degenerate sequences with broad vocabulary usage and strong cross-view consistency. On TIMIT retrieval, it preserves edit-distance search while reducing archive token count by 55%. A continuous-sweep probe shows lower local overlap than a dense geometric tokenizer, but stronger length control and bounded edit trajectories under 100 ms shifts. PairAlign is a sequence-symbolic predictive learner: like JEPA-style objectives, it predicts an abstract target from another view as a learned variable-length symbolic sequence, not a continuous latent.

Related papers

• Rethinking Item Tokenization in Generative Recommenders: From Fixed Atoms to Semantic Subwords [50.621722853036005]
  In generative recommender systems, items are typically tokenized into fixed-length semantic ID sequences for autoregressive next-item prediction.<n>For user-context modeling, this fine-grained representation triggers Intra-item Attention Overload.<n>We propose Semantic Subword Tokenization (SST), which represents historical items as variable-length semantic subwords.
  arXiv  Detail & Related papers  (2026-08-24T02:42:51Z)
• Token-to-Token Alignment of Text Embeddings for Semantic Blending [55.88554156801394]
  We introduce Token-to-Token alignment, a framework that establishes explicit semantic correspondence between tokens across prompts.<n>Our results show that text embedding spaces in text-to-image models implicitly encode a continuous semantic structure that becomes accessible once representations are properly aligned.
  arXiv  Detail & Related papers  (2026-06-22T23:54:40Z)
• SegCompass: Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning Segmentation [46.07708619404428]
  Seg is an end-to-end model that leverages a Sparse Autoencoder to forge an explicit, interpretable, and differentiable alignment pathway.<n>A "white-box" connection that is significantly more traceable than latent queries and more coherent than textual readouts.
  arXiv  Detail & Related papers  (2026-05-21T15:59:39Z)
• Exploring Token-Space Manipulation in Latent Audio Tokenizers [33.022035588157614]
  We propose the Latent Audio Tokenizer for Token-space Editing (LATTE)<n>LATTE appends a fixed set of learnable latent tokens to the audio feature sequence and retains only these tokens for quantization and decoding.<n>We show that the resulting tokenizer preserves competitive reconstruction quality in low-bitrate speech coding settings.
  arXiv  Detail & Related papers  (2026-05-11T19:58:14Z)
• Zonkey: A Hierarchical Diffusion Language Model with Differentiable Tokenization and Probabilistic Attention [0.0]
  Zonkey is a hierarchical diffusion model that addresses limitations through a fully trainable pipeline from raw characters to document-level representations.<n>At its core is a differentiable tokenizer that learns probabilistic beginning-of-sequence (BOS) decisions.<n>Zonkey generates coherent, variable-length text from noise, demonstrating emergent hierarchies.
  arXiv  Detail & Related papers  (2026-01-29T14:17:37Z)
• DSA-Tokenizer: Disentangled Semantic-Acoustic Tokenization via Flow Matching-based Hierarchical Fusion [28.204167153140506]
  Speech tokenizers serve as the cornerstone of discrete Speech Large Language Models.<n>We propose DSA-Tokenizer, which explicitly disentangles speech into discrete semantic and acoustic tokens.
  arXiv  Detail & Related papers  (2026-01-14T07:22:24Z)
• MergeDNA: Context-aware Genome Modeling with Dynamic Tokenization through Token Merging [65.07273789940116]
  This paper introduces a hierarchical architecture that jointly optimize a dynamic genomic tokenizer and latent Transformers with context-aware pre-training tasks.<n> MergeDNA achieves superior performance on three popular DNA benchmarks and several multi-omics tasks with fine-tuning or zero-shot evaluation.
  arXiv  Detail & Related papers  (2025-11-17T19:27:41Z)
• VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models [35.38573641029626]
  We introduce the novel task of Extreme Short Token Reduction, which aims to represent entire videos using a minimal set of discrete tokens.<n>On the Extreme Short Token Reduction task, our VQToken compresses sequences to just 0.07 percent of their original length while incurring only a 0.66 percent drop in accuracy on the NextQA-MC benchmark.
  arXiv  Detail & Related papers  (2025-03-21T09:46:31Z)
• CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens [49.569695524535454]
  We propose to represent speech with supervised semantic tokens, which are derived from a multilingual speech recognition model by inserting vector quantization into the encoder. Based on the tokens, we further propose a scalable zero-shot TTS synthesizer, CosyVoice, which consists of an LLM for text-to-token generation and a conditional flow matching model for token-to-speech synthesis.
  arXiv  Detail & Related papers  (2024-07-07T15:16:19Z)
• Linear-Time Modeling of Linguistic Structure: An Order-Theoretic Perspective [97.57162770792182]
  Tasks that model the relation between pairs of tokens in a string are a vital part of understanding natural language. We show that these exhaustive comparisons can be avoided, and, moreover, the complexity can be reduced to linear by casting the relation between tokens as a partial order over the string. Our method predicts real numbers for each token in a string in parallel and sorts the tokens accordingly, resulting in total orders of the tokens in the string.
  arXiv  Detail & Related papers  (2023-05-24T11:47:35Z)
• Byte Pair Encoding for Symbolic Music [0.0]
  Byte Pair embeddings significantly decreases the sequence length while increasing the vocabulary size. We leverage the embedding capabilities of such models with more expressive tokens, resulting in both better results and faster inference in generation and classification tasks. The source code is shared on Github, along with a companion website.
  arXiv  Detail & Related papers  (2023-01-27T20:22:18Z)
• Fast End-to-End Speech Recognition via a Non-Autoregressive Model and Cross-Modal Knowledge Transferring from BERT [72.93855288283059]
  We propose a non-autoregressive speech recognition model called LASO (Listen Attentively, and Spell Once) The model consists of an encoder, a decoder, and a position dependent summarizer (PDS)
  arXiv  Detail & Related papers  (2021-02-15T15:18:59Z)
• Consistent Multiple Sequence Decoding [36.46573114422263]
  We introduce a consistent multiple sequence decoding architecture. This architecture allows for consistent and simultaneous decoding of an arbitrary number of sequences. We show the efficacy of our consistent multiple sequence decoder on the task of dense relational image captioning.
  arXiv  Detail & Related papers  (2020-04-02T00:43:54Z)

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.