MoRoVoc: A Large Dataset for Geographical Variation Identification of the Spoken Romanian Language

• URL: http://arxiv.org/abs/2509.16781v1
• Date: Sat, 20 Sep 2025 19:06:51 GMT
• Title: MoRoVoc: A Large Dataset for Geographical Variation Identification of the Spoken Romanian Language
• Abstract summary: MoRoVoc is the largest dataset for analyzing the regional variation of spoken Romanian.<n>We propose a multi-target adversarial training framework for speech models that incorporates demographic attributes as adversarial targets.
• Score: 3.074263534235215
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper introduces MoRoVoc, the largest dataset for analyzing the regional variation of spoken Romanian. It has more than 93 hours of audio and 88,192 audio samples, balanced between the Romanian language spoken in Romania and the Republic of Moldova. We further propose a multi-target adversarial training framework for speech models that incorporates demographic attributes (i.e., age and gender of the speakers) as adversarial targets, making models discriminative for primary tasks while remaining invariant to secondary attributes. The adversarial coefficients are dynamically adjusted via meta-learning to optimize performance. Our approach yields notable gains: Wav2Vec2-Base achieves 78.21% accuracy for the variation identification of spoken Romanian using gender as an adversarial target, while Wav2Vec2-Large reaches 93.08% accuracy for gender classification when employing both dialect and age as adversarial objectives.

Related papers

• Bias in the Ear of the Listener: Assessing Sensitivity in Audio Language Models Across Linguistic, Demographic, and Positional Variations [21.050704978484784]
  We construct and release the BiasInEar dataset, a speech-augmented benchmark based on Global MMLU Lite.<n>We evaluate nine representative models under linguistic (language and accent), demographic (gender), and structural (option order) perturbations.<n>Our findings reveal that MLLMs are relatively robust to demographic factors but highly sensitive to language and option order, suggesting that speech can amplify existing structural biases.
  arXiv  Detail & Related papers  (2026-02-01T05:34:34Z)
• Demographic Attributes Prediction from Speech Using WavLM Embeddings [25.00298717665857]
  This paper introduces a general classifier based on WavLM features, to infer demographic characteristics, such as age, gender, native language, education, and country, from speech.<n>The proposed framework identifies key acoustic and linguistic fea-tures associated with demographic attributes, achieving a Mean Absolute Error (MAE) of 4.94 for age prediction and over 99.81% accuracy for gender classification.
  arXiv  Detail & Related papers  (2025-02-17T16:43:47Z)
• Speechworthy Instruction-tuned Language Models [71.8586707840169]
  We show that both prompting and preference learning increase the speech-suitability of popular instruction-tuned LLMs. We share lexical, syntactical, and qualitative analyses to showcase how each method contributes to improving the speech-suitability of generated responses.
  arXiv  Detail & Related papers  (2024-09-23T02:34:42Z)
• Sonos Voice Control Bias Assessment Dataset: A Methodology for Demographic Bias Assessment in Voice Assistants [10.227469020901232]
  This paper introduces the Sonos Voice Control Bias Assessment dataset. 1,038 speakers, 166 hours, 170k audio samples, with 9,040 unique labelled transcripts. Results show statistically significant differences in performance across age, dialectal region and ethnicity.
  arXiv  Detail & Related papers  (2024-05-14T12:53:32Z)
• SpeechAlign: Aligning Speech Generation to Human Preferences [51.684183257809075]
  We introduce SpeechAlign, an iterative self-improvement strategy that aligns speech language models to human preferences. We show that SpeechAlign can bridge the distribution gap and facilitate continuous self-improvement of the speech language model.
  arXiv  Detail & Related papers  (2024-04-08T15:21:17Z)
• RoDia: A New Dataset for Romanian Dialect Identification from Speech [28.458975585210947]
  RoDia is the first dataset for Romanian dialect identification from speech. Includes speech samples from five distinct regions of Romania, covering both urban and rural environments. Top scoring model achieves a macro F1 score of 59.83% and a micro F1 score of 62.08%, indicating that the task is challenging.
  arXiv  Detail & Related papers  (2023-09-06T21:56:24Z)
• NLP-CIC @ DIACR-Ita: POS and Neighbor Based Distributional Models for Lexical Semantic Change in Diachronic Italian Corpora [62.997667081978825]
  We present our systems and findings on unsupervised lexical semantic change for the Italian language. The task is to determine whether a target word has evolved its meaning with time, only relying on raw-text from two time-specific datasets. We propose two models representing the target words across the periods to predict the changing words using threshold and voting schemes.
  arXiv  Detail & Related papers  (2020-11-07T11:27:18Z)
• Cross-lingual Spoken Language Understanding with Regularized Representation Alignment [71.53159402053392]
  We propose a regularization approach to align word-level and sentence-level representations across languages without any external resource. Experiments on the cross-lingual spoken language understanding task show that our model outperforms current state-of-the-art methods in both few-shot and zero-shot scenarios.
  arXiv  Detail & Related papers  (2020-09-30T08:56:53Z)
• The Unreasonable Effectiveness of Machine Learning in Moldavian versus Romanian Dialect Identification [24.182791316595576]
  Follow-up on the Moldavian versus Romanian Cross-Dialect Topic Identification shared task of VarDial 2019 Evaluation Campaign. Experiments show that ML models can accurately identify the dialects, even at the sentence level and across different domains. We propose an improved ML model using ensemble learning.
  arXiv  Detail & Related papers  (2020-07-30T19:25:00Z)
• Unsupervised Cross-lingual Representation Learning for Speech Recognition [63.85924123692923]
  XLSR learns cross-lingual speech representations by pretraining a single model from the raw waveform of speech in multiple languages. We build on wav2vec 2.0 which is trained by solving a contrastive task over masked latent speech representations. Experiments show that cross-lingual pretraining significantly outperforms monolingual pretraining.
  arXiv  Detail & Related papers  (2020-06-24T18:25:05Z)
• Learning to Learn Morphological Inflection for Resource-Poor Languages [105.11499402984482]
  We propose to cast the task of morphological inflection - mapping a lemma to an indicated inflected form - for resource-poor languages as a meta-learning problem. Treating each language as a separate task, we use data from high-resource source languages to learn a set of model parameters. Experiments with two model architectures on 29 target languages from 3 families show that our suggested approach outperforms all baselines.
  arXiv  Detail & Related papers  (2020-04-28T05:13:17Z)

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.