Lexical Tone is Hard to Quantize: Probing Discrete Speech Units in Mandarin and Yorùbá

• URL: http://arxiv.org/abs/2604.07467v1
• Date: Wed, 08 Apr 2026 18:07:04 GMT
• Title: Lexical Tone is Hard to Quantize: Probing Discrete Speech Units in Mandarin and Yorùbá
• Abstract summary: Discrete speech units (DSUs) are derived by quantising representations from models trained using self-supervised learning (SSL)<n>We show that DSUs encode suprasegmental information less reliably than segmental structure.<n>Our investigations using the tone languages Mandarin and Yorb show that the SSL latent representations themselves do encode tone, yet DSUs obtained using quantisation tend to prioritise phonetic structure.
• Score: 6.024575966427832
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Discrete speech units (DSUs) are derived by quantising representations from models trained using self-supervised learning (SSL). They are a popular representation for a wide variety of spoken language tasks, including those where prosody matters. DSUs are especially convenient for tasks where text and speech are jointly modelled, such as text-to-speech and multimodal dialogue systems. But we have found that DSUs encode suprasegmental information less reliably than segmental structure, which we demonstrate in this work using lexical tone, though this limitation likely extends to other suprasegmental features such as prosody. Our investigations using the tone languages Mandarin and Yorùbá show that the SSL latent representations themselves do encode tone, yet DSUs obtained using quantisation tend to prioritise phonetic structure, which makes lexical tone less reliably encoded. This remains true for a variety of quantisation methods, not only the most common, K-means. We conclude that current DSU quantisation strategies have limitations for suprasegmental features, which suggests a need for new, tone-aware (or prosody-aware) techniques in speech representation learning. We point towards a potential form of the solution by performing K-means clustering once to encode phonetic information, then again on the residual representation, which better encodes lexical tone.

Related papers

• Speech Codec Probing from Semantic and Phonetic Perspectives [49.01048570474675]
  Speech tokenizers are essential for connecting speech to large language models (LLMs) in multimodal systems.<n> emerging evidence suggests that what is termed "semantic" in speech representations does not align with text-derived semantics.
  arXiv  Detail & Related papers  (2026-03-11T03:32:25Z)
• BEST-STD: Bidirectional Mamba-Enhanced Speech Tokenization for Spoken Term Detection [8.303512060791736]
  Spoken term detection is often hindered by reliance on frame-level features and the computationally intensive DTW-based template matching.<n>We propose a novel approach that encodes speech into discrete, speaker-agnostic semantic tokens.<n>This facilitates fast retrieval using text-based search algorithms and effectively handles out-of-vocabulary terms.
  arXiv  Detail & Related papers  (2024-11-21T13:05:18Z)
• Do Discrete Self-Supervised Representations of Speech Capture Tone Distinctions? [13.197705351799215]
  We evaluate whether discrete symbols adequately capture tone in two example languages, Mandarin and Yoruba. We find that using discrete symbols leads to a substantial loss of tone information, even for language-specialised SSL models.
  arXiv  Detail & Related papers  (2024-10-25T19:13:25Z)
• 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)
• 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)
• DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding [51.32965203977845]
  We propose the use of discrete speech units (DSU) instead of continuous-valued speech encoder outputs. The proposed model shows robust performance on speech inputs from seen/unseen domains and instruction-following capability in spoken question answering. Our findings suggest that the ASR task and datasets are not crucial in instruction-tuning for spoken question answering tasks.
  arXiv  Detail & Related papers  (2024-06-13T17:28:13Z)
• 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)
• Preliminary study on using vector quantization latent spaces for TTS/VC systems with consistent performance [55.10864476206503]
  We investigate the use of quantized vectors to model the latent linguistic embedding. By enforcing different policies over the latent spaces in the training, we are able to obtain a latent linguistic embedding. Our experiments show that the voice cloning system built with vector quantization has only a small degradation in terms of perceptive evaluations.
  arXiv  Detail & Related papers  (2021-06-25T07:51:35Z)
• Unsupervised Cross-Modal Audio Representation Learning from Unstructured Multilingual Text [69.55642178336953]
  We present an approach to unsupervised audio representation learning. Based on a triplet neural network architecture, we harnesses semantically related cross-modal information to estimate audio track-relatedness. We show that our approach is invariant to the variety of annotation styles as well as to the different languages of this collection.
  arXiv  Detail & Related papers  (2020-03-27T07:37:15Z)

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.