Technical report: Impact of Duration Prediction on Speaker-specific TTS for Indian Languages

• URL: http://arxiv.org/abs/2507.16875v1
• Date: Tue, 22 Jul 2025 09:38:30 GMT
• Title: Technical report: Impact of Duration Prediction on Speaker-specific TTS for Indian Languages
• Authors: Isha Pandey, Pranav Gaikwad, Amruta Parulekar, Ganesh Ramakrishnan,
• Abstract summary: We train a non-autoregressive Continuous Normalizing Flow (CNF) based speech model using publicly available Indian language data.<n>We evaluate multiple duration prediction strategies for zero-shot, speaker-specific generation.
• Score: 16.782842482372427
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: High-quality speech generation for low-resource languages, such as many Indian languages, remains a significant challenge due to limited data and diverse linguistic structures. Duration prediction is a critical component in many speech generation pipelines, playing a key role in modeling prosody and speech rhythm. While some recent generative approaches choose to omit explicit duration modeling, often at the cost of longer training times. We retain and explore this module to better understand its impact in the linguistically rich and data-scarce landscape of India. We train a non-autoregressive Continuous Normalizing Flow (CNF) based speech model using publicly available Indian language data and evaluate multiple duration prediction strategies for zero-shot, speaker-specific generation. Our comparative analysis on speech-infilling tasks reveals nuanced trade-offs: infilling based predictors improve intelligibility in some languages, while speaker-prompted predictors better preserve speaker characteristics in others. These findings inform the design and selection of duration strategies tailored to specific languages and tasks, underscoring the continued value of interpretable components like duration prediction in adapting advanced generative architectures to low-resource, multilingual settings.

Related papers

• A2TTS: TTS for Low Resource Indian Languages [16.782842482372427]
  We present a speaker conditioned text-to-speech (TTS) system aimed at generating speech for unseen speakers.<n>Using a diffusion-based TTS architecture, a speaker encoder extracts embeddings from short reference audio samples to condition the DDPM decoder for multispeaker generation.<n>We employ a cross-attention based duration prediction mechanism that utilizes reference audio, enabling more accurate and speaker consistent timing.
  arXiv  Detail & Related papers  (2025-07-21T06:20:27Z)
• An Initial Investigation of Language Adaptation for TTS Systems under Low-resource Scenarios [76.11409260727459]
  This paper explores the language adaptation capability of ZMM-TTS, a recent SSL-based multilingual TTS system. We demonstrate that the similarity in phonetics between the pre-training and target languages, as well as the language category, affects the target language's adaptation performance.
  arXiv  Detail & Related papers  (2024-06-13T08:16:52Z)
• The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation [13.352795145385645]
  Speech translation (ST) is a good means of pretraining speech models for end-to-end spoken language understanding. We show that our models reach higher performance over baselines on monolingual and multilingual intent classification. We also create new benchmark datasets for speech summarization and low-resource/zero-shot transfer from English to French or Spanish.
  arXiv  Detail & Related papers  (2023-05-16T17:53:03Z)
• Adapting Multilingual Speech Representation Model for a New, Underresourced Language through Multilingual Fine-tuning and Continued Pretraining [2.3513645401551333]
  We investigate the possibility for adapting an existing multilingual wav2vec 2.0 model for a new language. Our results show that continued pretraining is the most effective method to adapt a wav2vec 2.0 model for a new language. We find that if a model pretrained on a related speech variety or an unrelated language with similar phonological characteristics is available, multilingual fine-tuning using additional data from that language can have positive impact on speech recognition performance.
  arXiv  Detail & Related papers  (2023-01-18T03:57:53Z)
• Towards Building Text-To-Speech Systems for the Next Billion Users [18.290165216270452]
  We evaluate the choice of acoustic models, vocoders, supplementary loss functions, training schedules, and speaker and language diversity for Dravidian and Indo-Aryan languages. We train and evaluate TTS models for 13 languages and find our models to significantly improve upon existing models in all languages as measured by mean opinion scores.
  arXiv  Detail & Related papers  (2022-11-17T13:59:34Z)
• Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation [70.81596088969378]
  Cross-lingual Outline-based Dialogue dataset (termed COD) enables natural language understanding. COD enables dialogue state tracking, and end-to-end dialogue modelling and evaluation in 4 diverse languages.
  arXiv  Detail & Related papers  (2022-01-31T18:11:21Z)
• 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)
• Exploring Teacher-Student Learning Approach for Multi-lingual Speech-to-Intent Classification [73.5497360800395]
  We develop an end-to-end system that supports multiple languages. We exploit knowledge from a pre-trained multi-lingual natural language processing model.
  arXiv  Detail & Related papers  (2021-09-28T04:43:11Z)
• Towards Zero-shot Language Modeling [90.80124496312274]
  We construct a neural model that is inductively biased towards learning human languages. We infer this distribution from a sample of typologically diverse training languages. We harness additional language-specific side information as distant supervision for held-out languages.
  arXiv  Detail & Related papers  (2021-08-06T23:49:18Z)
• Linguistic Typology Features from Text: Inferring the Sparse Features of World Atlas of Language Structures [73.06435180872293]
  We construct a recurrent neural network predictor based on byte embeddings and convolutional layers. We show that some features from various linguistic types can be predicted reliably.
  arXiv  Detail & Related papers  (2020-04-30T21:00:53Z)

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.