Flexible and Interpretable Accent Distance Measurements

• URL: http://arxiv.org/abs/2609.11458v1
• Date: Thu, 10 Sep 2026 12:32:13 GMT
• Title: Flexible and Interpretable Accent Distance Measurements
• Abstract summary: A phonetics researcher may demonstrate accent variation by comparing vowel formants in paired recordings of individual words.<n>These results will be interpretable, but the recordings will be time-consuming to collect and may not be representative of connected speech.<n> Accented Text-to-Speech research has pushed towards using accent embeddings derived from accent classification tasks.<n>These embeddings can be produced from any speech recording, but are not readily interpretable.<n>In this paper, we demonstrate that articulatory representations created through articulatory inversion can be used as an interpretable basis for accent comparison.
• Score: 34.004131445310215
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Determining the differences between two speakers' accents is a fundamental task in linguistics and speech technology research. The methodology used to measure these differences depends on the specific research area. A phonetics researcher may demonstrate accent variation by comparing vowel formants in paired recordings of individual words. These results will be interpretable, but the recordings will be time-consuming to collect and may not be representative of connected speech. Accented Text-to-Speech (TTS) research has pushed towards using accent embeddings derived from accent classification tasks. These embeddings can be produced from any speech recording, but are not readily interpretable. In this paper, we demonstrate that articulatory representations created through articulatory inversion can be used as an interpretable basis for accent comparison and that optimal transport provides a framework for accent comparison across arbitrary recording types.

Related papers

• Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents [3.6734440150955368]
  Audio language models (ALMs) are increasingly used for speech-based understanding.<n>The effects of accent variation, domain shift, and semantic over-inference on audio reasoning are poorly understood.<n>We evaluate audio language models across five semantic and paralinguistic reasoning tasks.
  arXiv  Detail & Related papers  (2026-05-11T20:27:40Z)
• Quantifying Speaker Embedding Phonological Rule Interactions in Accented Speech Synthesis [44.55147169458465]
  We analyze the interaction between speaker embeddings and linguistically motivated phonological rules in accented speech synthesis.<n>Experiments show that combining rules with embeddings yields more authentic accents.<n>Our findings highlight rules as a lever for accent control and a framework for evaluating disentanglement in speech generation.
  arXiv  Detail & Related papers  (2026-01-20T19:25:33Z)
• SpeechR: A Benchmark for Speech Reasoning in Large Audio-Language Models [60.72029578488467]
  SpeechR is a unified benchmark for evaluating reasoning over speech in large audio-language models.<n>It evaluates models along three key dimensions: factual retrieval, procedural inference, and normative judgment.<n> Evaluations on eleven state-of-the-art LALMs reveal that high transcription accuracy does not translate into strong reasoning capabilities.
  arXiv  Detail & Related papers  (2025-08-04T03:28:04Z)
• On the Relationship between Accent Strength and Articulatory Features [26.865464238029748]
  This paper explores the relationship between accent strength and articulatory features inferred from acoustic speech.<n>The proposed framework leverages recent self-supervised learning articulatory inversion techniques to estimate articulatory features.<n>Results indicate that tongue positioning patterns distinguish the two dialects, with notable differences inter-dialects in rhotic and low back vowels.
  arXiv  Detail & Related papers  (2025-07-03T20:08:28Z)
• Languages in Multilingual Speech Foundation Models Align Both Phonetically and Semantically [58.019484208091534]
  Cross-lingual alignment in pretrained language models (LMs) has enabled efficient transfer in text-based LMs.<n>It remains an open question whether findings and methods from text-based cross-lingual alignment apply to speech.
  arXiv  Detail & Related papers  (2025-05-26T07:21:20Z)
• Pairwise Evaluation of Accent Similarity in Speech Synthesis [11.513055793492418]
  We aim to enhance both subjective and objective evaluation methods for accent similarity.<n>We refine the XAB listening test by adding components that achieve higher statistical significance with fewer listeners and lower costs.<n>We utilise pronunciation-related metrics, based on distances between vowel formants and phonetic posteriorgrams, to evaluate accent generation.
  arXiv  Detail & Related papers  (2025-05-20T14:23:50Z)
• ExPO: Explainable Phonetic Trait-Oriented Network for Speaker Verification [48.98768967435808]
  We use computational method to verify if an utterance matches the identity of an enrolled speaker.<n>Despite much success, we have yet to develop a speaker verification system that offers explainable results.<n>A novel approach, Explainable Phonetic Trait-Oriented (ExPO) network, is proposed in this paper to introduce the speaker's phonetic trait.
  arXiv  Detail & Related papers  (2025-01-10T05:53:37Z)
• Speech Rhythm-Based Speaker Embeddings Extraction from Phonemes and Phoneme Duration for Multi-Speaker Speech Synthesis [16.497022070614236]
  This paper proposes a speech rhythm-based method for speaker embeddings to model phoneme duration using a few utterances by the target speaker. A novel feature of the proposed method is the rhythm-based embeddings extracted from phonemes and their durations, which are known to be related to speaking rhythm.
  arXiv  Detail & Related papers  (2024-02-11T02:26:43Z)
• An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation [57.68765353264689]
  Speech enhancement and speech separation are two related tasks. Traditionally, these tasks have been tackled using signal processing and machine learning techniques. Deep learning has been exploited to achieve strong performance.
  arXiv  Detail & Related papers  (2020-08-21T17:24:09Z)
• Continuous speech separation: dataset and analysis [52.10378896407332]
  In natural conversations, a speech signal is continuous, containing both overlapped and overlap-free components. This paper describes a dataset and protocols for evaluating continuous speech separation algorithms.
  arXiv  Detail & Related papers  (2020-01-30T18:01:31Z)

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.