Do Discrete Self-Supervised Representations of Speech Capture Tone Distinctions?

• URL: http://arxiv.org/abs/2410.19935v1
• Date: Fri, 25 Oct 2024 19:13:25 GMT
• Title: Do Discrete Self-Supervised Representations of Speech Capture Tone Distinctions?
• Authors: Opeyemi Osakuade, Simon King,
• Abstract summary: 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.
• Score: 13.197705351799215
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Discrete representations of speech, obtained from Self-Supervised Learning (SSL) foundation models, are widely used, especially where there are limited data for the downstream task, such as for a low-resource language. Typically, discretization of speech into a sequence of symbols is achieved by unsupervised clustering of the latents from an SSL model. Our study evaluates whether discrete symbols - found using k-means - adequately capture tone in two example languages, Mandarin and Yoruba. We compare latent vectors with discrete symbols, obtained from HuBERT base, MandarinHuBERT, or XLS-R, for vowel and tone classification. We find that using discrete symbols leads to a substantial loss of tone information, even for language-specialised SSL models. We suggest that discretization needs to be task-aware, particularly for tone-dependent downstream tasks.

Related papers

• The Limits of Data Scaling: Sub-token Utilization and Acoustic Saturation in Multilingual ASR [6.627057618324123]
  We analyze Whisper's decoding behavior during inference across 49 languages.<n>We study the utilization pattern of the model's sub-token space.
  arXiv  Detail & Related papers  (2025-10-26T02:13:26Z)
• Benchmarking Prosody Encoding in Discrete Speech Tokens [13.60092490447892]
  This study focuses on prosodic encoding based on their sensitivity to the artificially modified prosody, aiming to provide practical guidelines for designing discrete tokens.<n>In particular, speech language models are expected to understand and generate responses that reflect not only the semantic content but also prosodic features.
  arXiv  Detail & Related papers  (2025-08-15T05:11:16Z)
• SSLR: A Semi-Supervised Learning Method for Isolated Sign Language Recognition [2.409285779772107]
  Sign language recognition systems aim to recognize sign gestures and translate them into spoken language. One of the main challenges in SLR is the scarcity of annotated datasets. We propose a semi-supervised learning approach for SLR, employing a pseudo-label method to annotate unlabeled samples.
  arXiv  Detail & Related papers  (2025-04-23T11:59:52Z)
• LatentQA: Teaching LLMs to Decode Activations Into Natural Language [72.87064562349742]
  We introduce LatentQA, the task of answering open-ended questions about model activations in natural language. We propose Latent Interpretation Tuning (LIT), which finetunes a decoder LLM on a dataset of activations and associated question-answer pairs. Our decoder also specifies a differentiable loss that we use to control models, such as debiasing models on stereotyped sentences and controlling the sentiment of generations.
  arXiv  Detail & Related papers  (2024-12-11T18:59:33Z)
• What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysis [44.93152068353389]
  Self-supervised learning (SSL) has attracted increased attention for learning meaningful speech representations. Speaker SSL models adopt utterance-level training objectives primarily for speaker representation.
  arXiv  Detail & Related papers  (2024-01-31T07:23:22Z)
• Towards the extraction of robust sign embeddings for low resource sign language recognition [7.969704867355098]
  We show that keypoint-based embeddings can transfer between sign languages and achieve competitive performance. We furthermore achieve better performance using fine-tuned transferred embeddings than models trained only on the target sign language.
  arXiv  Detail & Related papers  (2023-06-30T11:21:40Z)
• Self-supervised Neural Factor Analysis for Disentangling Utterance-level Speech Representations [30.293081541301746]
  Self-supervised learning (SSL) speech models such as wav2vec and HuBERT have demonstrated state-of-the-art performance on automatic speech recognition. We argue that the problem is caused by the lack of disentangled representations and an utterance-level learning objective. Our models outperform the current best model, WavLM, on all utterance-level non-semantic tasks on the SUPERB benchmark with only 20% of labeled data.
  arXiv  Detail & Related papers  (2023-05-14T08:26:24Z)
• SLICER: Learning universal audio representations using low-resource self-supervised pre-training [53.06337011259031]
  We present a new Self-Supervised Learning approach to pre-train encoders on unlabeled audio data. Our primary aim is to learn audio representations that can generalize across a large variety of speech and non-speech tasks.
  arXiv  Detail & Related papers  (2022-11-02T23:45:33Z)
• Combining Spectral and Self-Supervised Features for Low Resource Speech Recognition and Translation [27.857955394020475]
  Self-Supervised Learning (SSL) models have been successfully applied in various deep learning-based speech tasks. The quality of SSL representations depends highly on the relatedness between the SSL training domain(s) and the target data domain. We propose a learnable and interpretable framework to combine SF and SSL representations.
  arXiv  Detail & Related papers  (2022-04-05T20:09:15Z)
• Self-Supervised Learning for speech recognition with Intermediate layer supervision [52.93758711230248]
  We propose Intermediate Layer Supervision for Self-Supervised Learning (ILS-SSL) ILS-SSL forces the model to concentrate on content information as much as possible by adding an additional SSL loss on the intermediate layers. Experiments on LibriSpeech test-other set show that our method outperforms HuBERT significantly.
  arXiv  Detail & Related papers  (2021-12-16T10:45:05Z)
• 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)
• Sign Language Recognition via Skeleton-Aware Multi-Model Ensemble [71.97020373520922]
  Sign language is commonly used by deaf or mute people to communicate. We propose a novel Multi-modal Framework with a Global Ensemble Model (GEM) for isolated Sign Language Recognition ( SLR) Our proposed SAM- SLR-v2 framework is exceedingly effective and achieves state-of-the-art performance with significant margins.
  arXiv  Detail & Related papers  (2021-10-12T16:57:18Z)
• Multi-Modal Zero-Shot Sign Language Recognition [51.07720650677784]
  We propose a multi-modal Zero-Shot Sign Language Recognition model. A Transformer-based model along with a C3D model is used for hand detection and deep features extraction. A semantic space is used to map the visual features to the lingual embedding of the class labels.
  arXiv  Detail & Related papers  (2021-09-02T09:10:39Z)
• 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)
• Variable-rate discrete representation learning [20.81400194698063]
  We propose slow autoencoders for unsupervised learning of high-level variable-rate discrete representations of sequences. We show that the resulting event-based representations automatically grow or shrink depending on the density of salient information in the input signals. We develop run-length Transformers for event-based representation modelling and use them to construct language models in the speech domain.
  arXiv  Detail & Related papers  (2021-03-10T14:42:31Z)
• Video-based Sign Language Recognition without Temporal Segmentation [88.03159640595187]
  We propose a novel continuous sign recognition framework, which eliminates the preprocessing of temporal segmentation.<n>The proposed LS-HAN consists of three components: a two-stream Convolutional Neural Network (CNN) for video feature representation generation, a Latent Space for semantic gap bridging, and a Hierarchical Attention Network (HAN) for latent space based recognition.
  arXiv  Detail & Related papers  (2018-01-30T17:37:42Z)

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.