English
Related papers

Related papers: Vividh-ASR: A Complexity-Tiered Benchmark and Opti…

200 papers

Meetings are a valuable yet challenging scenario for speech applications due to complex acoustic conditions. This paper summarizes the outcomes of the MISP 2025 Challenge, hosted at Interspeech 2025, which focuses on multi-modal,…

Despite decades of research on reverberant speech, comparing methods remains difficult because most corpora lack per-file acoustic annotations or provide limited documentation for reproduction. We present RIR-Mega-Speech, a corpus of…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-29 Mandip Goswami

Pashto is spoken by approximately 60--80 million people but has no published benchmarks for multilingual automatic speech recognition (ASR) on any shared public test set. This paper reports the first reproducible multi-model evaluation on…

Computation and Language · Computer Science 2026-04-07 Hanif Rahman

Automatic speech recognition (ASR) training can utilize multiple experts as teacher models, each trained on a specific domain or accent. Teacher models may be opaque in nature since their architecture may be not be known or their training…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-29 Aakriti Agrawal , Milind Rao , Anit Kumar Sahu , Gopinath Chennupati , Andreas Stolcke

Recent advances in machine learning have demonstrated that multi-modal pre-training can improve automatic speech recognition (ASR) performance compared to randomly initialized models, even when models are fine-tuned on uni-modal tasks.…

Computation and Language · Computer Science 2024-04-01 Yash Jain , David Chan , Pranav Dheram , Aparna Khare , Olabanji Shonibare , Venkatesh Ravichandran , Shalini Ghosh

The field of Singing Voice Synthesis (SVS) has seen significant advancements in recent years due to the rapid progress of diffusion-based approaches. However, capturing vocal style, genre-specific pitch inflections, and language-dependent…

Sound · Computer Science 2025-12-01 Sandipan Dhar , Mayank Gupta , Preeti Rao

This study evaluates the feasibility of lightweight Whisper models (Tiny, Base, Small) for Urdu speech recognition in low-resource settings. Despite Urdu being the 10th most spoken language globally with over 230 million speakers, its…

Computation and Language · Computer Science 2025-08-14 Abdul Rehman Antall , Naveed Akhtar

In this paper, we present a bias and sustainability focused investigation of Automatic Speech Recognition (ASR) systems, namely Whisper and Massively Multilingual Speech (MMS), which have achieved state-of-the-art (SOTA) performances.…

Computation and Language · Computer Science 2025-03-04 Ajinkya Kulkarni , Atharva Kulkarni , Miguel Couceiro , Isabel Trancoso

Large-scale end-to-end models such as Whisper have shown strong performance on diverse speech tasks, but their internal behavior on pathological speech remains poorly understood. Understanding how dysarthric speech is represented across…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-07 Zhengjun Yue , Devendra Kayande , Zoran Cvetkovic , Erfan Loweimi

We address the problem of efficient acoustic-model refinement (continuous retraining) using semi-supervised and active learning for a low resource Indian language, wherein the low resource constraints are having i) a small labeled corpus…

Computation and Language · Computer Science 2018-10-17 Maharajan Chellapriyadharshini , Anoop Toffy , Srinivasa Raghavan K. M. , V Ramasubramanian

In this paper, we propose a self-training approach for automatic speech recognition (ASR) for low-resource settings. While self-training approaches have been extensively developed and evaluated for high-resource languages such as English,…

Computation and Language · Computer Science 2023-08-11 Satwinder Singh , Feng Hou , Ruili Wang

Modern automatic speech recognition (ASR) models, such as OpenAI's Whisper, rely on deep encoder-decoder architectures, and their encoders are a critical bottleneck for efficient deployment due to high computational intensity. We introduce…

Machine Learning · Computer Science 2025-08-26 Keisuke Kamahori , Jungo Kasai , Noriyuki Kojima , Baris Kasikci

We present a cost-effective approach for developing Automatic Speech Recognition (ASR) models for low-resource languages like Ika. We fine-tune the pretrained wav2vec 2.0 Massively Multilingual Speech Models on a high-quality speech dataset…

Computation and Language · Computer Science 2024-10-03 Uchenna Nzenwata , Daniel Ogbuigwe

Automatic speech recognition replaces typing only when correction costs less than manual entry, a threshold determined by error types, not counts: fixing a misrecognized domain term costs far more than inserting a comma. Word error rate…

Computation and Language · Computer Science 2026-05-21 Kavya Manohar , Arghya Bhattacharya , Kush Juvekar , Kumarmanas Nethil

Automatic detection of speaker confidence is critical for adaptive computing but remains constrained by limited labelled data and the subjectivity of paralinguistic annotations. This paper proposes a semi-supervised hybrid framework that…

Sound · Computer Science 2026-05-13 Adam Wynn , Jingyun Wang

An ideal speech recognition model has the capability to transcribe speech accurately under various characteristics of speech signals, such as speaking style (read and spontaneous), speech context (formal and informal), and background noise…

Computation and Language · Computer Science 2024-10-15 Aulia Adila , Dessi Lestari , Ayu Purwarianti , Dipta Tanaya , Kurniawati Azizah , Sakriani Sakti

Speech self-supervised models such as wav2vec 2.0 and HuBERT are making revolutionary progress in Automatic Speech Recognition (ASR). However, they have not been totally proven to produce better performance on tasks other than ASR. In this…

Computation and Language · Computer Science 2022-10-05 Yingzhi Wang , Abdelmoumene Boumadane , Abdelwahab Heba

Indigenous languages are a fundamental legacy in the development of human communication, embodying the unique identity and culture of local communities in America. The Second AmericasNLP (Americas Natural Language Processing) Competition…

Computation and Language · Computer Science 2024-09-24 Monica Romero , Sandra Gomez , Ivan G. Torre

This paper explores the pitfalls in evaluating multilingual automatic speech recognition (ASR) models, with a particular focus on Indic language scripts. We investigate the text normalization routine employed by leading ASR models,…

Computation and Language · Computer Science 2024-11-12 Kavya Manohar , Leena G Pillai , Elizabeth Sherly

Speaker adaptation is important to build robust automatic speech recognition (ASR) systems. In this work, we investigate various methods for speaker adaptive training (SAT) based on feature-space approaches for a conformer-based acoustic…

Computation and Language · Computer Science 2022-06-28 Mohammad Zeineldeen , Jingjing Xu , Christoph Lüscher , Ralf Schlüter , Hermann Ney