arXiv AI
Jun 3
BaltiVoice: A Speech Corpus and Fine-tuned Whisper ASR System for the Balti Language
arXiv:2606. 03504v1 Announce Type: cross Abstract: We present BaltiVoice, a 16.
BaltiVoice: A Speech Corpus and Fine-tuned Whisper ASR System for the Balti Language
We present BaltiVoice, a 16. 8-hour read-speech corpus for Balti (ISO 639-3: bft), a Tibetic language spoken in Gilgit-Baltistan, Pakistan, with no prior publicly available ASR resources.
Related stories
arXiv Computation and Language
Aug 27
Fine-Tuning Whisper for Automatic Speech Recognition in Baniwa: A Preliminary Study
The study fine‑tunes the Whisper Small model for Automatic Speech Recognition (ASR) in Baniwa, an indigenous Arawakan language. Using a 0.54‑hour corpus of 1,373 manually transcribed recordings, the fine‑tuned model achieved a Word Error Rate of 37.5% and a Character Error Rate of 7.45%. These results provide an initial baseline for Baniwa ASR and suggest that multilingual foundation models can be adapted to extremely low‑resource languages.
arXiv Machine Learning
Jul 21
Robust Assamese Speech Recognition through Controlled Fine-Tuning of Whisper Models
arXiv:2607. 17164v1 Announce Type: new Abstract: Developing Automatic Speech Recognition (ASR) for morphologically rich, low-resource languages such as Assamese is challenging due to insufficient annotated speech data.
arXiv Computation and Language
Aug 24
Building and Evaluating a Synthetic Bengali Speech Resource for Telecom Customer Care
The paper introduces a synthetic Bengali speech dataset tailored for telecom customer‑care applications, comprising 10,000 audio‑text pairs (≈26.82 hours) with predefined train, validation, and test splits. The data were generated using OmniVoice voice‑cloning, and include both original and normalized transcripts for ASR/STT use. Automatic intelligibility evaluation with a fine‑tuned Whisper model shows an average WER of 2.54% and CER of 0.59%, indicating strong text‑audio consistency, while the authors note limitations of synthetic speech and STT‑based evaluation.
arXiv Computation and Language
Sep 15
Neyshekar: An Open Persian Read-Speech Corpus for Automatic Speech Recognition
arXiv:2609.14542v1 Announce Type: new Abstract: Neyshekar is presented as an open Persian read-speech corpus designed for coverage of both formal and informal language, named entities, and longer utt...
arXiv AI
Aug 14
Comparative Analysis of Multilingual Pre-trained Models for Nepali Automatic Speech Recognition
arXiv:2608. 12327v1 Announce Type: cross Abstract: Multilingual pretrained models nominally support Nepali, yet no controlled benchmark has compared them under a single fine-tuning protocol.
arXiv AI
Jul 28
Indic DiarBench: A Multilingual Joint Diarization and ASR Benchmark for Indian Languages
arXiv:2607. 23808v1 Announce Type: cross Abstract: In this work, we introduce Indic DiarBench, a speaker diarization and ASR benchmark dataset spanning all 22 scheduled languages of India.
arXiv AI
Jul 16
When Audio Separation Hurts Zero-Shot ASR: Evaluating SAM-Audio with Whisper on Bengali and English Speech
arXiv:2603. 04710v2 Announce Type: replace-cross Abstract: Recent advances in automatic speech recognition (ASR) and speech enhancement have strengthened the common belief that cleaner audio should lead to more accurate transcription.
arXiv Computation and Language
Sep 22
Vimarsha: Faithful ASR Evaluation for Indian Languages with Demographic Diversity, In-the-Wild Audio and Spelling Variations
arXiv:2609.24199v1 Announce Type: new Abstract: Evaluation benchmarks for Indian language automatic speech recognition (ASR) suffer from two systematic biases: optimistic scores from clean, controlle...
arXiv AI
Jun 9
Subtitle-Aligned Fine-Tuning of Whisper for Swiss German ASR: Benchmark Contamination, Convention Mismatch, and an Honest Baseline at 25.6% WER (13.8% cWER)
arXiv:2606. 07608v1 Announce Type: cross Abstract: We present a systematic study of fine-tuning OpenAI's Whisper large-v3 for Swiss German ASR, using 1,367 hours of broadcast speech paired with Standard German subtitles as weak supervision.
arXiv Computation and Language
3d ago
TutlAit v1: a crowdsourced Moroccan Tamazight speech dataset with Arabic transcriptions and regional accent labels
The TutlAit v1 dataset is a crowdsourced corpus of Moroccan Tamazight speech paired with Modern Standard Arabic transcriptions and explicit regional accent labels. It contains 13,384 audio files (≈20.9 hours) collected via a web application, with volunteers contributing through text‑to‑audio and audio‑to‑text workflows, and includes additional segments from freely available media. The dataset covers Atlas, Souss, Rif, and Kabyle varieties, making it a valuable resource for speech recognition, translation, and accent identification in an under‑resourced language.
arXiv Computation and Language
Sep 3
SpeakPay: Domain-Adaptive LoRA Fine-Tuning of Whisper for Low-Resource Nepali Financial Speech Recognition
SpeakPay is a voice‑first digital wallet designed to make mobile payment apps in Nepal accessible to visually impaired users. The paper introduces NepFinSpeech‑403, a 403‑utterance Nepali financial voice command dataset, and demonstrates that fine‑tuning Whisper large‑v2 with LoRA reduces the Word Error Rate from 129.95% to 42.58% and improves Devanagari numeral recognition from 0.0% to 73.9%. Domain adaptation also boosts the Transaction Success Rate from 1.67% to 33.33%, with as few as 100 domain‑specific utterances halving the zero‑shot WER.