English
Related papers

Related papers: Bolbosh: Script-Aware Flow Matching for Kashmiri T…

200 papers

Recent years have witnessed a trend that large language model (LLM) based text-to-speech (TTS) emerges into the mainstream due to their high naturalness and zero-shot capacity. In this paradigm, speech signals are discretized into token…

Evaluation of Text to Speech (TTS) systems is challenging and resource-intensive. Subjective metrics such as Mean Opinion Score (MOS) are not easily comparable between works. Objective metrics are frequently used, but rarely validated…

Sound · Computer Science 2026-03-03 Christoph Minixhofer , Ondrej Klejch , Peter Bell

While modern Text-to-Speech (TTS) systems achieve high fidelity for read-style speech, they struggle to generate Autonomous Sensory Meridian Response (ASMR), a specialized, low-intensity speech style essential for relaxation. The inherent…

Sound · Computer Science 2026-01-23 Leying Zhang , Tingxiao Zhou , Haiyang Sun , Mengxiao Bi , Yanmin Qian

If today some African languages like Swahili have enough resources to develop high-performing Natural Language Processing (NLP) systems, many other languages spoken on the continent are still lacking such support. For these languages, still…

Computation and Language · Computer Science 2024-12-19 Naira Abdou Mohamed , Zakarya Erraji , Abdessalam Bahafid , Imade Benelallam

Deepfake audio detection is challenging for low-resource languages like Bengali due to limited datasets and subtle acoustic features. To address this, we introduce BangalFake, a Bengali Deepfake Audio Dataset with 12,260 real and 13,260…

Sound · Computer Science 2025-05-19 Istiaq Ahmed Fahad , Kamruzzaman Asif , Sifat Sikder

Recent advancements in multimodal large language models (MLLMs) have aimed to integrate and interpret data across diverse modalities. However, the capacity of these models to concurrently process and reason about multiple modalities remains…

Few-shot speaker adaptation is a specific Text-to-Speech (TTS) system that aims to reproduce a novel speaker's voice with a few training data. While numerous attempts have been made to the few-shot speaker adaptation system, there is still…

Audio and Speech Processing · Electrical Eng. & Systems 2021-08-17 Ji-Hoon Kim , Sang-Hoon Lee , Ji-Hyun Lee , Hong-Gyu Jung , Seong-Whan Lee

Collecting high-quality studio recordings of audio is challenging, which limits the language coverage of text-to-speech (TTS) systems. This paper proposes a framework for scaling a multilingual TTS model to 100+ languages using found data…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-17 Takaaki Saeki , Gary Wang , Nobuyuki Morioka , Isaac Elias , Kyle Kastner , Fadi Biadsy , Andrew Rosenberg , Bhuvana Ramabhadran , Heiga Zen , Françoise Beaufays , Hadar Shemtov

Despite the advances in neural text to speech (TTS), many Arabic dialectal varieties remain marginally addressed, with most resources concentrated on Modern Spoken Arabic (MSA) and Gulf dialects, leaving Egyptian Arabic -- the most widely…

Computation and Language · Computer Science 2026-03-30 Ahmed Khaled Khamis , Hesham Ali

In this work, we explore multiple architectures and training procedures for developing a multi-speaker and multi-lingual neural TTS system with the goals of a) improving the quality when the available data in the target language is limited…

Computation and Language · Computer Science 2021-08-18 Javier Latorre , Charlotte Bailleul , Tuuli Morrill , Alistair Conkie , Yannis Stylianou

Video dubbing requires content accuracy, expressive prosody, high-quality acoustics, and precise lip synchronization, yet existing approaches struggle on all four fronts. To address these issues, we propose DiFlowDubber, the first video…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Ngoc-Son Nguyen , Thanh V. T. Tran , Jeongsoo Choi , Hieu-Nghia Huynh-Nguyen , Truong-Son Hy , Van Nguyen

Developing automatic speech recognition (ASR) systems for low-resource languages is hindered by the scarcity of transcribed corpora. This proof-of-concept study explores songs as an unconventional yet promising data source for Kazakh ASR.…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-10 Rustem Yeshpanov

Prosody is essential for speech technology, shaping comprehension, naturalness, and expressiveness. However, current text-to-speech (TTS) systems still struggle to accurately capture human-like prosodic variation, in part because existing…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-05 Cedric Chan , Jianjing Kuang

Large, openly licensed speech datasets are essential for building automatic speech recognition (ASR) systems, yet many widely spoken languages remain underrepresented in public resources. Pashto, spoken by more than 60 million people, has…

Computation and Language · Computer Science 2026-02-17 Jandad Jahani , Mursal Dawodi , Jawid Ahmad Baktash

End-to-end text-to-speech (TTS) systems have been developed for European languages like English and Spanish with state-of-the-art speech quality, prosody, and naturalness. However, development of end-to-end TTS for Indian languages is…

Computation and Language · Computer Science 2022-12-08 Ankur Debnath , Shridevi S Patil , Gangotri Nadiger , Ramakrishnan Angarai Ganesan

Despite 230 million speakers, Urdu remains critically under-resourced in speech technology. We introduce UrduSpeech: a large high-fidelity Urdu corpus comprising 156 hours of audio with 12-dimension paralinguistic metadata, encompassing…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-19 Attia Nafees ul Haq , Zeyu Zhu , Jingbin Hu , ChunJiang He , Lei Xie

The language diversity in India's education sector poses a significant challenge, hindering inclusivity. Despite the democratization of knowledge through online educational content, the dominance of English, as the internet's lingua franca,…

Computation and Language · Computer Science 2024-03-08 Sai Akarsh , Vamshi Raghusimha , Anindita Mondal , Anil Vuppala

Recent advances in text-to-speech (TTS) synthesis, particularly those leveraging large language models (LLMs), have significantly improved expressiveness and naturalness. However, generating human-like, interactive dialogue speech remains…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-28 Hanke Xie , Dake Guo , Chengyou Wang , Yue Li , Wenjie Tian , Xinfa Zhu , Xinsheng Wang , Xiulin Li , Guanqiong Miao , Bo Liu , Lei Xie

This paper introduces StyleSpeech, a novel Text-to-Speech~(TTS) system that enhances the naturalness and accuracy of synthesized speech. Building upon existing TTS technologies, StyleSpeech incorporates a unique Style Decorator structure…

Sound · Computer Science 2024-12-31 Haowei Lou , Helen Paik , Wen Hu , Lina Yao

Solving Bengali Math Word Problems (MWPs) remains a major challenge in natural language processing (NLP) due to the language's low-resource status and the multi-step reasoning required. Existing models struggle with complex Bengali MWPs,…

Computation and Language · Computer Science 2025-07-31 Bidyarthi Paul , Jalisha Jashim Era , Mirazur Rahman Zim , Tahmid Sattar Aothoi , Faisal Muhammad Shah